publications

2026

1. 

   Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models

   Basel Mousi, Fahim Dalvi, Shammur Chowdhury , and 2 more authors

   In Proceedings of Interspeech 2026 , 2026

   accepted

   Bib

   @inproceedings{mousi2026said,
     title = {Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models},
     author = {Mousi, Basel and Dalvi, Fahim and Chowdhury, Shammur and Alam, Firoj and Durrani, Nadir},
     booktitle = {Proceedings of Interspeech 2026},
     year = {2026},
     address = {Sydney, Australia},
     url = {https://arxiv.org/pdf/2608.27135},
     note = {accepted},
   }

2. ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation

   Samir Abdaljalil, Hunzalah Hassan Bhatti, Ahlam Bashiti , and 11 more authors

   In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026) , Oct 2026

   Bib

   @inproceedings{abdaljalil2026imageeval,
     title = {ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation},
     author = {Abdaljalil, Samir and Bhatti, Hunzalah Hassan and Bashiti, Ahlam and Amir, Farina and Hasan, Md Arid and Mousi, Basel and Durrani, Nadir and Dalvi, Fahim and Ali, Zien Sheikh and Serpedin, Erchin and Kurban, Hasan and Jarrar, Mustafa and Chowdhury, Shammur Absar and Alam, Firoj},
     booktitle = {Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026)},
     year = {2026},
     address = {Budapest, Hungary},
     month = oct,
     url = {https://arxiv.org/pdf/2608.30475},
     publisher = {Association for Computational Linguistics},
   }

3. 

   AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes

   Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Abul Hasnat , and 3 more authors

   In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026) , Oct 2026

   Bib

   @inproceedings{kmainasi2026aha,
     title = {{AHA-Memes}: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes},
     author = {Kmainasi, Mohamed Bayan and Shahroor, Ali Ezzat and Hasnat, Abul and Biswas, Md Rafiul and Zaghouani, Wajdi and Alam, Firoj},
     booktitle = {Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026)},
     address = {Budapest, Hungary},
     month = oct,
     year = {2026},
     publisher = {Association for Computational Linguistics},
     url = {https://arxiv.org/abs/2607.27393},
   }

4. 

   Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling

   Tajwaar Shafiq, Hunzalah Hassan Bhatti, Firoj Alam , and 1 more author

   In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026) , Oct 2026

   Bib

   @inproceedings{shafiq2026aslemanadi2026data,
     title = {{Aslema} at {NADI} 2026: Data Augmentation for Intent Recognition and Slot Filling},
     author = {Shafiq, Tajwaar and Bhatti, Hunzalah Hassan and Alam, Firoj and Chowdhury, Shammur Absar},
     booktitle = {Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026)},
     year = {2026},
     address = {Budapest, Hungary},
     month = oct,
     publisher = {Association for Computational Linguistics},
     url = {https://arxiv.org/abs/2608.18689},
   }

5. ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts

   Firoj Alam, Md Rafiul Biswas, Mohamed Bayan Kmainasi , and 5 more authors

   In Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026) , Oct 2026

   Bib

   @inproceedings{alam2026arguard,
     title = {{ArGuard} Shared Task: Harmful Content Detection in Arabic Memes and {LLM} Prompts},
     author = {Alam, Firoj and Biswas, Md Rafiul and Kmainasi, Mohamed Bayan and Shahroor, Ali Ezzat and Mubarak, Hamdy and Mikros, George and Hasnat, Abul and Zaghouani, Wajdi},
     booktitle = {Proceedings of the Fourth Arabic Natural Language Processing Conference (ArabicNLP 2026)},
     year = {2026},
     address = {Budapest, Hungary},
     month = oct,
     publisher = {Association for Computational Linguistics},
     url = {https://arxiv.org/abs/2609.29349},
   }

6. 

   ProBel: Propaganda Detection with Techniques, Spans, and Explanations

   Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Elisa Sartori , and 2 more authors

   arXiv preprint arXiv:2608.22388, Oct 2026

   Bib

   @article{kmainasi2026probel,
     title = {{ProBel}: Propaganda Detection with Techniques, Spans, and Explanations},
     author = {Kmainasi, Mohamed Bayan and Shahroor, Ali Ezzat and Sartori, Elisa and Da San Martino, Giovanni and Alam, Firoj},
     journal = {arXiv preprint arXiv:2608.22388},
     year = {2026},
     url = {https://arxiv.org/abs/2608.22388},
   }

7. When Do VLMs Help Arabic Manuscript OCR? A Cross-Dataset Study

   Moshiur Farazi, Firoj Alam, Abderrahmane Maaradji , and 3 more authors

   arXiv preprint arXiv:2608.22366, Oct 2026

   Bib

   @article{farazi2026vlms,
     title = {When Do VLMs Help Arabic Manuscript OCR? A Cross-Dataset Study},
     author = {Farazi, Moshiur and Alam, Firoj and Maaradji, Abderrahmane and Maamar, Zakaria and Mubarak, Hamdy and Zaghouani, Wajdi},
     journal = {arXiv preprint arXiv:2608.22366},
     year = {2026},
     url = {https://arxiv.org/abs/2608.22366},
   }

8. Findings of the WMT 2026 Shared Task on Low-Resource Arabic-Asian Language Translation

   Sahinur Rahman Laskar, Firoj Alam, Bishwaraj Paul , and 3 more authors

   In Proceedings of the Eleventh Conference on Machine Translation (WMT) , Oct 2026

   Bib

   @inproceedings{laskar2026findings,
     title = {Findings of the {WMT} 2026 Shared Task on Low-Resource Arabic-Asian Language Translation},
     author = {Laskar, Sahinur Rahman and Alam, Firoj and Paul, Bishwaraj and Ahmad, Irfan and Lydia, Maya Silvi and Dadure, Pankaj},
     booktitle = {Proceedings of the Eleventh Conference on Machine Translation (WMT)},
     pages = {1124--1137},
     year = {2026},
     month = oct,
     publisher = {Association for Computational Linguistics},
   }

9. 

   Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

   Syeda Faiza Ahmed Sara, Zien Sheikh Ali, Hunzalah Hassan Bhatti , and 2 more authors

   In Findings of the Association for Computational Linguistics: EMNLP 2026 , Oct 2026

   Accepted for publication

   Bib

   @inproceedings{ahmed2026multiturn,
     title = {Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges},
     author = {Sara, Syeda Faiza Ahmed and Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Alam, Firoj and Chowdhury, Shammur Absar},
     booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
     year = {2026},
     address = {Budapest, Hungary},
     month = oct,
     note = {Accepted for publication},
     url = {https://arxiv.org/abs/2608.17605},
   }

10. 

    WASIL: In-the-Wild Arabic Spoken Interactions with LLMs

    Zien Sheikh Ali, Hamdy Mubarak, Soon-Gyo Jung , and 3 more authors

    In Proceedings of Interspeech 2026 , Oct 2026

    accepted

    Bib

    @inproceedings{ali2026wasilinthewildarabicspoken,
      title = {{WASIL}: In-the-Wild Arabic Spoken Interactions with LLMs},
      author = {Ali, Zien Sheikh and Mubarak, Hamdy and Jung, Soon-Gyo and Bhatti, Hunzalah Hassan and Alam, Firoj and Chowdhury, Shammur Absar},
      booktitle = {Proceedings of Interspeech 2026},
      year = {2026},
      address = {Sydney, Australia},
      note = {accepted},
      url = {https://arxiv.org/abs/2605.16364}
    }

11. 

    Adapting reinforcement learning with chain-of-thought supervision for explainable detection of hateful and propagandistic memes

    Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor , and 2 more authors

    Machine Learning with Applications, Oct 2026

    Abs Bib

    Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone. Although thinking-based multimodal large language models (MLLMs) have advanced vision-language understanding, their application to meme content moderation remains underexplored. We propose a reinforcement learning-based post-training method that improves classification performance and reference-based explanation quality in thinking-based MLLMs via task-specific rewards and Group Relative Policy Optimization (GRPO). Concretely, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful and propagandistic meme understanding across English and Arabic benchmarks, (ii) extend existing meme datasets with weakly supervised chain-of-thought (CoT) rationales via distillation and multi-LLM fine-grained propaganda annotations, (iii) introduce a GRPO-based objective with thinking-length regularization that jointly optimizes classification accuracy and explanation quality, and (iv) investigate self-training GRPO (ST-GRPO) on unlabeled memes using consensus-based pseudo-labels. Experiments on the Hateful Memes and ArMeme benchmarks show that our approach improves over previously reported results on FHM accuracy (up to +2.1%, from 79.9% to 82.0%) and on ArMeme macro-F1 (up to +7.6 points, from 0.536 to 0.612 with explanations; +6.1 compared to the original ArMeme benchmark), while also generating natural-language explanations. On ArMeme, sequence-classification baselines remain stronger in terms of raw accuracy, whereas our approach provides more balanced per-class performance along with explanations. We publicly release our code, data extensions, and evaluation resources.

    @article{kmainasi2026adapting,
      title = {Adapting reinforcement learning with chain-of-thought supervision for explainable detection of hateful and propagandistic memes},
      journal = {Machine Learning with Applications},
      pages = {101003},
      year = {2026},
      issn = {2666-8270},
      doi = {https://doi.org/10.1016/j.mlwa.2026.101003},
      url = {https://www.sciencedirect.com/science/article/pii/S2666827026001684},
      author = {Kmainasi, Mohamed Bayan and Kutlu, Mucahid and Shahroor, Ali Ezzat and Hasnat, Abul and Alam, Firoj},
      keywords = {Hateful meme detection, Propaganda detection, Multimodal large language models, Reinforcement learning, Chain-of-thought reasoning},
    }

12. Beyond Logical Forms: LLM-Extracted Patterns for Fallacy Classification

    Eleni Papadopulos, Firoj Alam, and Giovanni Da San Martino

    In Proceedings of the 13th Workshop on Argument Mining and Reasoning , Jul 2026

    Bib

    @inproceedings{papadopulos-etal-2026-beyond,
      title = {Beyond Logical Forms: {LLM}-Extracted Patterns for Fallacy Classification},
      author = {Papadopulos, Eleni and Alam, Firoj and Da San Martino, Giovanni},
      editor = {Elaraby, Mohamed and Hautli-Janisz, Annette and Romberg, Julia and Musi, Elena and Ruggeri, Federico and Lawrence, John},
      booktitle = {Proceedings of the 13th Workshop on Argument Mining and Reasoning},
      month = jul,
      year = {2026},
      address = {San Diego, California, USA},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.argmining-1.2/},
      pages = {5--18},
      isbn = {979-8-89176-399-9},
    }

13. 

    JAMAL: A Multidimensional Benchmark for Arabic Commonsense Reasoning Across Life-Domains and Cognitive Axes

    Basma Sayah, Attia Nehar, Hadda Cherroun , and 2 more authors

    BenchCouncil Transactions on Benchmarks, Standards and Evaluations, Jun 2026

    Abs Bib

    Commonsense is a broad and multifaceted concept, making its evaluation a persistent challenge in natural language processing (NLP). This paper introduces JAMAL (Arabic for “Camel”), a multidimensional framework and benchmark for Arabic commonsense reasoning. JAMAL is structured along three complementary axes: (i) a life-domain axis comprising a taxonomy of 56 functional categories informed by the World Health Organization’s International Classification of Functioning, Disability, and Health (ICF), capturing diverse aspects of daily human experience; (ii) a cognitive axis organizing commonsense into three reasoning types: everyday situations, general knowledge, and problem-solving; and (iii) a cultural grounding axis distinguishing between universal, Western/global, and Arabic-specific knowledge. To operationalize this framework, benchmark items are constructed using psycholinguistically inspired principles of constrained contextual prediction. We evaluate five Arabic language models using JAMAL and observe consistent differences in their performance across all axes. Notably, FANAR-27B achieves the strongest overall results among all evaluated models, outperforming FANAR-9B and smaller baselines. Overall, JAMAL provides a structured and interpretable benchmark for evaluating commonsense reasoning in Arabic, supporting the development of more robust language models through systematic analysis of their behavioral limitations.

    @article{jamal2026multidimensional,
      title = {{JAMAL}: A Multidimensional Benchmark for Arabic Commonsense Reasoning Across Life-Domains and Cognitive Axes},
      author = {Sayah, Basma and Nehar, Attia and Cherroun, Hadda and Bellaouar, Slimane and Alam, Firoj},
      journal = {BenchCouncil Transactions on Benchmarks, Standards and Evaluations},
      volume = {6},
      year = {2026},
      month = jun,
      doi = {10.66834/byjwsd23},
      url = {https://journal.benchcouncil.org/TBench/article/view/66},
    }

14. 

    Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation

    Firoj Alam, Gagan Bhatia, Sahinur Rahman Laskar , and 1 more author

    arXiv preprint arXiv:2604.05083, Jun 2026

    Bib

    @article{alam2026llm-judge,
      title = {Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation},
      author = {Alam, Firoj and Bhatia, Gagan and Laskar, Sahinur Rahman and Chowdhury, Shammur Absar},
      journal = {arXiv preprint arXiv:2604.05083},
      year = {2026},
      url = {https://arxiv.org/abs/2604.05083},
    }

15. Can Thinking Models Think to Detect Hateful Memes?

    Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor , and 2 more authors

    In Companion Proceedings of the ACM Web Conference 2026 , United Arab Emirates, Jun 2026

    Abs Bib

    Hateful memes often require compositional multimodal reasoning: the image and text may appear benign in isolation, yet their interaction conveys harmful intent. Although thinking-based multimodal large language models (MLLMs) have recently advanced vision–language understanding, their capabilities remain underexplored for hateful meme analysis. We propose a reinforcement learning–based post-training framework that improves reasoning in thinking-based MLLMs via task-specific rewards and a novel Group Relative Policy Optimization (GRPO) objective. Concretely, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful meme understanding, (ii) extend an existing hateful meme dataset by generating weakly/pseudo-supervised chain-of-thought (CoT) rationales via distillation, and (iii) introduce a GRPO-based objective that jointly optimizes meme classification and explanation quality to encourage fine-grained step-by-step reasoning. Experiments on the Hateful Memes benchmark show that our approach achieves state-of-the-art results, improving accuracy and F1 by approximately 1% and explanation quality by approximately 3%. We will publicly release our code, data extensions, and evaluation resources to support reproducibility.

    @inproceedings{bayan2026can,
      author = {Kmainasi, Mohamed Bayan and Kutlu, Mucahid and Ezzat Shahroor, Ali and Hasnat, Abul and Alam, Firoj},
      title = {Can Thinking Models Think to Detect Hateful Memes?},
      year = {2026},
      isbn = {9798400723087},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA},
      url = {https://arxiv.org/pdf/2603.01225},
      doi = {10.1145/3774905.3795465},
      booktitle = {Companion Proceedings of the ACM Web Conference 2026},
      pages = {935–944},
      numpages = {10},
      keywords = {hateful meme detection, multimodal large language models, reinforcement learning, multimodal reasoning},
      location = {United Arab Emirates},
      series = {WWW Companion '26},
    }

16. 

    CritiSense: Critical Digital Literacy and Resilience Against Misinformation

    Firoj Alam, Fatema Ahmad, Ali Ezzat Shahroor , and 5 more authors

    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) , Jul 2026

    Bib

    @inproceedings{alam-etal-2026-critisense,
      title = {{C}riti{S}ense: Critical Digital Literacy and Resilience Against Misinformation},
      author = {Alam, Firoj and Ahmad, Fatema and Shahroor, Ali Ezzat and Kmainasi, Mohamed Bayan and Sartori, Elisa and Da San Martino, Giovanni and Hasnat, Abul and Ali, Raian},
      editor = {Durrett, Greg and Jian, Ping},
      booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)},
      month = jul,
      year = {2026},
      address = {San Diego, California, United States},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.acl-demo.48/},
      pages = {481--492},
      isbn = {979-8-89176-392-0},
    }

17. 

    Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA

    Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh , and 7 more authors

    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) , Jul 2026

    Bib

    @inproceedings{abbas-etal-2026-fanar,
      title = {Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic {QA}},
      author = {Abbas, Ummar and Ouzzani, Mourad and Eltabakh, Mohamed Y. and Sinan, Omar and Bhatia, Gagan and Mubarak, Hamdy and Hawasly, Majd and Hashim, Mohammed Qusay and Darwish, Kareem Mohamed and Alam, Firoj},
      editor = {Li, Yunyao and Rehm, Georg and Tu, Mei},
      booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)},
      month = jul,
      year = {2026},
      address = {San Diego, California, USA},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.acl-industry.109/},
      pages = {1567--1588},
      isbn = {979-8-89176-394-4},
    }

18. 

    Advances in AI Systems on Islamic Knowledge Capabilities: A Critical Survey

    Gagan Bhatia, Hamdy Mubarak, Majd Hawasly , and 9 more authors

    Feb 2026

    Bib

    @article{Bhatia_2026,
      title = {Advances in AI Systems on Islamic Knowledge Capabilities: A Critical Survey},
      publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
      author = {Bhatia, Gagan and Mubarak, Hamdy and Hawasly, Majd and Jarrar, Mustafa and Mikros, George and Zaraket, Fadi and Alhirthani, Mahmoud and Al-Khatib, Mutaz and Cochrane, Logan and Darwish, Kareem and Yahiaoui, Rashid and Alam, Firoj},
      url = {http://dx.doi.org/10.36227/techrxiv.177155997.77147487/v1},
      doi = {10.36227/techrxiv.177155997.77147487/v1},
      year = {2026},
      month = feb,
    }

19. 

    MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs

    Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi , and 2 more authors

    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing , Oct 2026

    Bib

    @inproceedings{ali2026menaspeechbank,
      title = {{MENASpeechBank}: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for {AudioLLMs}},
      author = {Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Nandi, Rabindra Nath and Chowdhury, Shammur Absar and Alam, Firoj},
      booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
      address = {Budapest, Hungary},
      publisher = {Association for Computational Linguistics},
      month = oct,
      year = {2026},
      url = {https://arxiv.org/abs/2602.07036},
    }

20. 

    MemeLens: Multilingual Multitask VLMs for Memes

    Ali Ezzat Shahroor, Mohamed Bayan Kmainasi, Abul Hasnat , and 4 more authors

    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing , Oct 2026

    Bib

    @inproceedings{shahroor2026memelens,
      title = {{MemeLens}: Multilingual Multitask {VLMs} for Memes},
      author = {Shahroor, Ali Ezzat and Kmainasi, Mohamed Bayan and Hasnat, Abul and Dimitrov, Dimitar and Da San Martino, Giovanni and Nakov, Preslav and Alam, Firoj},
      booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},
      address = {Budapest, Hungary},
      publisher = {Association for Computational Linguistics},
      month = oct,
      year = {2026},
      url = {https://arxiv.org/abs/2601.12539},
    }

21. 

    Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs

    Hunzalah Hassan Bhatti, Firoj Alam, and Shammur Absar Chowdhury

    In Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing , Nov 2026

    Accepted for publication

    Bib

    @inproceedings{bhatti2026multitask,
      title = {Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs},
      author = {Bhatti, Hunzalah Hassan and Alam, Firoj and Chowdhury, Shammur Absar},
      booktitle = {Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics and the 15th International Joint Conference on Natural Language Processing},
      year = {2026},
      address = {Hengqin, China},
      month = nov,
      note = {Accepted for publication},
      url = {https://arxiv.org/abs/2601.12494},
    }

22. 

    Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models

    Basel Mousi, Fahim Dalvi, Shammur Absar Chowdhury , and 2 more authors

    In Findings of the Association for Computational Linguistics: ACL 2026 , Jul 2026

    Bib

    @inproceedings{mousi-etal-2026-correct,
      title = {Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language Models},
      author = {Mousi, Basel and Dalvi, Fahim and Chowdhury, Shammur Absar and Alam, Firoj and Durrani, Nadir},
      editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
      booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
      month = jul,
      year = {2026},
      address = {San Diego, California, United States},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.findings-acl.234/},
      pages = {4763--4788},
      isbn = {979-8-89176-395-1},
    }

23. LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target

    Md Arid Hasan, Firoj Alam, Md Fahad Hossain , and 2 more authors

    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Jul 2026

    Bib

    @inproceedings{hasan-etal-2026-llm,
      title = {{LLM}-Based Multi-Task {B}angla Hate Speech Detection: Type, Severity, and Target},
      author = {Hasan, Md Arid and Alam, Firoj and Hossain, Md Fahad and Naseem, Usman and Ahmed, Syed Ishtiaque},
      editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
      booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
      month = jul,
      year = {2026},
      address = {San Diego, California, United States},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.acl-long.1565/},
      pages = {33962--33980},
      isbn = {979-8-89176-390-6},
    }

24. 

    POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization

    Usman Naseem, Robert Geislinger, Juan Ren , and 40 more authors

    In Findings of the Association for Computational Linguistics: ACL 2026 , Jul 2026

    Bib

    @inproceedings{naseem-etal-2026-polar,
      title = {{POLAR}: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization},
      author = {Naseem, Usman and Geislinger, Robert and Ren, Juan and Kohail, Sarah and Veliz, Rudy Alexandro Garrido and Sahil, P Sam and Zhang, Yiran and Abdulmumin, Idris and Stranisci, Marco Antonio and Alacam, {\"O}zge and Acarturk, Cengiz and Jabr, Aisha and Anwar, Saba and Ayele, Abinew Ali and Frenda, Simona and Cignarella, Alessandra Teresa and Tutubalina, Elena and Rogov, Oleg and Htet, Aung Kyaw and Wang, Xintong and Thapa, Surendrabikram and Rauniyar, Kritesh and Chakraborty, Tanmoy and Zeeshan, MD Arfeen and Kodati, Dheeraj and Keerthi, Satya and Moradizeyveh, Sahar and Alam, Firoj and Hasan, Md Arid and Ahmed, Syed Ishtiaque and Thu, Ye Kyaw and Parida, Shantipriya and Qazi, Ihsan Ayyub and Wanzare, Lilian Diana Awuor and Onyango, Nelson Odhiambo and Siro, Clemencia and Kimani, Jane Wanjiru and Ahmad, Ibrahim Said and Ali, Adem Chanie and Semmann, Martin and Biemann, Chris and Muhammad, Shamsuddeen Hassan and Yimam, Seid Muhie},
      editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
      booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
      month = jul,
      year = {2026},
      address = {San Diego, California, United States},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.findings-acl.1433/},
      pages = {28699--28720},
      isbn = {979-8-89176-395-1},
    }

25. Proceedings of the 16th International Workshop on Spoken Dialogue System Technology

    Feb 2026

    Bib

    @proceedings{iwsds-2026-1,
      title = {Proceedings of the 16th International Workshop on Spoken Dialogue System Technology},
      editor = {Riccardi, Giuseppe and Mousavi, Seyed Mahed and Torres, Maria Ines and Yoshino, Koichiro and Callejas, Zoraida and Chowdhury, Shammur Absar and Chen, Yun-Nung and Bechet, Frederic and Gustafson, Joakim and Damnati, G{\'e}raldine and Papangelis, Alex and D{'}Haro, Luis Fernando and Mendon{\c{c}}a, John and Bernardi, Raffaella and Hakkani-Tur, Dilek and Di Fabbrizio, Giuseppe {''}Pino{''} and Kawahara, Tatsuya and Alam, Firoj and Tur, Gokhan and Johnston, Michael},
      month = feb,
      year = {2026},
      address = {Trento, Italy},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.iwsds-1.0/},
    }

26. 

    SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization

    Usman Naseem, Robert Geislinger, Ada Ren , and 31 more authors

    In Proceedings of the 20th International Workshop on Semantic Evaluation (2026) , Jul 2026

    Bib

    @inproceedings{naseem-etal-2026-semeval,
      title = {{S}em{E}val-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization},
      author = {Naseem, Usman and Geislinger, Robert and Ren, Ada and Kohail, Sarah and Garrido Veliz, Rudy and Sahil, P Sam and Zhang, Yiran and Stranisci, Marco Antonio and Abdulmumin, Idris and Alacam, {\"O}zge and Acarturk, Cengiz and Jabr, Aisha and Anwar, Saba and Ayele, Abinew Ali and Tutubalina, Elena and Htet, Aung Kyaw and Wang, Xintong and Thapa, Surendrabikram and Chakraborty, Tanmoy and Kodati, Dheeraj and Moradizeyveh, Sahar and Alam, Firoj and Kyaw Thu, Ye and Parida, Shantipriya and Qazi, Ihsan Ayyub and Wanzare, Lilian Diana Awuor and Odhiambo, Nelson and Siro, Clemencia and Ahmad, Ibrahim Said and Ali, Adem Chanie and Semmann, Martin and Biemann, Chris and Muhammad, Shamsuddeen Hassan and Yimam, Seid Muhie},
      editor = {Kochmar, Ekaterina and Ghosh, Debanjan and North, Kai and Komachi, Mamoru},
      booktitle = {Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)},
      month = jul,
      year = {2026},
      address = {San Diego, California, USA},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2026.semeval-1.453/},
      pages = {3779--3796},
      isbn = {979-8-89176-414-9},
    }

27. 

    From RAG to Agentic RAG for Faithful Islamic Question Answering

    Gagan Bhatia, Hamdy Mubarak, Mustafa Jarrar , and 8 more authors

    In Findings of the Association for Computational Linguistics: ACL 2026 , Jul 2026

28. 

    Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants

    Hunzalah Hassan Bhatti, and Firoj Alam

    In The 15th edition of the Language Resources and Evaluation Conference (LREC 2026) , Jul 2026

    Bib

    @inproceedings{bhatti2025beyond,
      title = {{Beyond MCQ}: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants},
      author = {Bhatti, Hunzalah Hassan and Alam, Firoj},
      booktitle = {The 15th edition of the Language Resources and Evaluation Conference (LREC 2026)},
      year = {2026},
    }

2025

1. 

   OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA

   Firoj Alam, Ali Ezzat Shahroor, Md. Arid Hasan , and 8 more authors

   arXiv preprint arXiv:2510.06371, Jul 2025

   Bib

   @article{alam2025everydaymmqa,
     title = {{OASIS}: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA},
     author = {Alam, Firoj and Shahroor, Ali Ezzat and Hasan, Md. Arid and Ali, Zien Sheikh and Bhatti, Hunzalah Hassan and Kmainasi, Mohamed Bayan and Chowdhury, Shammur Absar and Mousi, Basel and Dalvi, Fahim and Durrani, Nadir and Milic-Frayling, Natasa},
     journal = {arXiv preprint arXiv:2510.06371},
     year = {2025},
   }

2. Annotating the Annotators: Analysis, Insights and Modelling from an Annotation Campaign on Persuasion Techniques Detection

   Davide Bassi, Dimitar Iliyanov Dimitrov, Bernardo D’Auria , and 7 more authors

   In Findings of the Association for Computational Linguistics: ACL 2025 , Jul 2025

   Bib

   @inproceedings{bassi-etal-2025-annotating,
     title = {Annotating the Annotators: Analysis, Insights and Modelling from an Annotation Campaign on Persuasion Techniques Detection},
     author = {Bassi, Davide and Dimitrov, Dimitar Iliyanov and D{'}Auria, Bernardo and Alam, Firoj and Hasanain, Maram and Moro, Christian and Orr{\`u}, Luisa and Turchi, Gian Piero and Nakov, Preslav and Da San Martino, Giovanni},
     editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
     booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
     month = jul,
     year = {2025},
     address = {Vienna, Austria},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.findings-acl.922/},
     doi = {10.18653/v1/2025.findings-acl.922},
     pages = {17918--17929},
     isbn = {979-8-89176-256-5},
   }

3. CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation

   Hunzalah Hassan Bhatti, Youssef Ahmed, Md Arid Hasan , and 1 more author

   In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks , Nov 2025

   Bib

   @inproceedings{hassan-bhatti-etal-2025-cultranai,
     title = {{C}ultran{AI} at {P}alm{X} 2025: Data Augmentation for Cultural Knowledge Representation},
     author = {Hassan Bhatti, Hunzalah and Ahmed, Youssef and Arid Hasan, Md and Alam, Firoj},
     editor = {Darwish, Kareem and Ali, Ahmed and Abu Farha, Ibrahim and Touileb, Samia and Zitouni, Imed and Abdelali, Ahmed and Al-Ghamdi, Sharefah and Alkhereyf, Sakhar and Zaghouani, Wajdi and Khalifa, Salam and AlKhamissi, Badr and Almatham, Rawan and Hamed, Injy and Alyafeai, Zaid and Alowisheq, Areeb and Inoue, Go and Mrini, Khalil and Alshammari, Waad},
     booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.arabicnlp-sharedtasks.111/},
     doi = {10.18653/v1/2025.arabicnlp-sharedtasks.111},
     pages = {809--817},
     isbn = {979-8-89176-356-2},
   }

4. MarsadLab at PalmX Shared Task: An LLM Benchmark for Arabic Culture and Islamic Civilization

   Md. Rafiul Biswas, Shimaa Ibrahim, Kais Attia , and 2 more authors

   In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks , Nov 2025

   Bib

   @inproceedings{rafiul-biswas-etal-2025-marsadlab-palmx,
     title = {{M}arsad{L}ab at {P}alm{X} Shared Task: An {LLM} Benchmark for {A}rabic Culture and Islamic Civilization},
     author = {Rafiul Biswas, Md. and Ibrahim, Shimaa and Attia, Kais and Alam, Firoj and Zaghouani, Wajdi},
     editor = {Darwish, Kareem and Ali, Ahmed and Abu Farha, Ibrahim and Touileb, Samia and Zitouni, Imed and Abdelali, Ahmed and Al-Ghamdi, Sharefah and Alkhereyf, Sakhar and Zaghouani, Wajdi and Khalifa, Salam and AlKhamissi, Badr and Almatham, Rawan and Hamed, Injy and Alyafeai, Zaid and Alowisheq, Areeb and Inoue, Go and Mrini, Khalil and Alshammari, Waad},
     booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.arabicnlp-sharedtasks.112/},
     doi = {10.18653/v1/2025.arabicnlp-sharedtasks.112},
     pages = {818--824},
     isbn = {979-8-89176-356-2},
   }

5. AYA at PalmX 2025: Modeling Cultural and Islamic Knowledge in LLMs

   Jannatul Tajrin, Bir Ballav Roy, and Firoj Alam

   In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks , Nov 2025

   Bib

   @inproceedings{tajrin-etal-2025-aya,
     title = {{AYA} at {P}alm{X} 2025: Modeling Cultural and Islamic Knowledge in {LLM}s},
     author = {Tajrin, Jannatul and Ballav Roy, Bir and Alam, Firoj},
     editor = {Darwish, Kareem and Ali, Ahmed and Abu Farha, Ibrahim and Touileb, Samia and Zitouni, Imed and Abdelali, Ahmed and Al-Ghamdi, Sharefah and Alkhereyf, Sakhar and Zaghouani, Wajdi and Khalifa, Salam and AlKhamissi, Badr and Almatham, Rawan and Hamed, Injy and Alyafeai, Zaid and Alowisheq, Areeb and Inoue, Go and Mrini, Khalil and Alshammari, Waad},
     booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.arabicnlp-sharedtasks.114/},
     doi = {10.18653/v1/2025.arabicnlp-sharedtasks.114},
     pages = {830--836},
     isbn = {979-8-89176-356-2},
   }

6. MarsadLab at AraGenEval Shared Task: LLM-Based Approaches to Arabic Authorship Style Transfer and Identification

   Md. Rafiul Biswas, Mabrouka Bessghaier, Firoj Alam , and 1 more author

   In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks , Nov 2025

   Bib

   @inproceedings{rafiul-biswas-etal-2025-marsadlab,
     title = {{M}arsad{L}ab at {A}ra{G}en{E}val Shared Task: {LLM}-Based Approaches to {A}rabic Authorship Style Transfer and Identification},
     author = {Rafiul Biswas, Md. and Bessghaier, Mabrouka and Alam, Firoj and Zaghouani, Wajdi},
     editor = {Darwish, Kareem and Ali, Ahmed and Abu Farha, Ibrahim and Touileb, Samia and Zitouni, Imed and Abdelali, Ahmed and Al-Ghamdi, Sharefah and Alkhereyf, Sakhar and Zaghouani, Wajdi and Khalifa, Salam and AlKhamissi, Badr and Almatham, Rawan and Hamed, Injy and Alyafeai, Zaid and Alowisheq, Areeb and Inoue, Go and Mrini, Khalil and Alshammari, Waad},
     booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.arabicnlp-sharedtasks.15/},
     doi = {10.18653/v1/2025.arabicnlp-sharedtasks.15},
     pages = {88--93},
     isbn = {979-8-89176-356-2},
   }

7. MAHED Shared Task: Multimodal Detection of Hope and Hate Emotions in Arabic Content

   Wajdi Zaghouani, Md. Rafiul Biswas, Mabrouka Bessghaier , and 4 more authors

   In Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks , Nov 2025

   Bib

   @inproceedings{zaghouani-etal-2025-mahed,
     title = {{MAHED} Shared Task: Multimodal Detection of Hope and Hate Emotions in {A}rabic Content},
     author = {Zaghouani, Wajdi and Biswas, Md. Rafiul and Bessghaier, Mabrouka and Ibrahim, Shimaa and Mikros, George and Hasnat, Abul and Alam, Firoj},
     editor = {Darwish, Kareem and Ali, Ahmed and Abu Farha, Ibrahim and Touileb, Samia and Zitouni, Imed and Abdelali, Ahmed and Al-Ghamdi, Sharefah and Alkhereyf, Sakhar and Zaghouani, Wajdi and Khalifa, Salam and AlKhamissi, Badr and Almatham, Rawan and Hamed, Injy and Alyafeai, Zaid and Alowisheq, Areeb and Inoue, Go and Mrini, Khalil and Alshammari, Waad},
     booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.arabicnlp-sharedtasks.75/},
     doi = {10.18653/v1/2025.arabicnlp-sharedtasks.75},
     pages = {560--574},
     isbn = {979-8-89176-356-2},
   }

8. BALSAM: A Platform for Benchmarking Arabic Large Language Models

   Rawan Nasser Almatham, Kareem Mohamed Darwish, Raghad Al-Rasheed , and 40 more authors

   In Proceedings of The Third Arabic Natural Language Processing Conference , Nov 2025

   Bib

   @inproceedings{almatham-etal-2025-balsam,
     title = {{BALSAM}: A Platform for Benchmarking {A}rabic Large Language Models},
     author = {Almatham, Rawan Nasser and Darwish, Kareem Mohamed and Al-Rasheed, Raghad and Alshammari, Waad Thuwaini and Alhoshan, Muneera and Almazrua, Amal and Al Wazrah, Asma and Alheraki, Mais and Alam, Firoj and Nakov, Preslav and Alzahrani, Norah A. and Albilali, Eman and Habash, Nizar and El-Sheikh, Abdelrahman Mustafa and Elmallah, Muhammad and Mubarak, Hamdy and Alyafeai, Zaid and Anwar, Mohamed and Li, Haonan and Abdelali, Ahmed and Altwairesh, Nora and Hasanain, Maram and Al-Thubaity, Abdulmohsen and Shehata, Shady and Alhafni, Bashar and Hamed, Injy and Inoue, Go and Elmadani, Khalid N. and Obeid, Ossama and Haouari, Fatima and Elsayed, Tamer and Alghamdi, Emad A. and Almubarak, Khalid and Alshahrani, Saied and Aljareh, Ola and Alajlan, Safa and Alshaqarawi, Areej and Alshihri, Maryam and Alghurabi, Sultana and Alzeghayer, Atikah and Altamimi, Afrah and Alfaifi, Abdullah and Alosaimy, Abdulrahman M},
     editor = {Darwish, Kareem and Ali, Ahmed and Abu Farha, Ibrahim and Touileb, Samia and Zitouni, Imed and Abdelali, Ahmed and Al-Ghamdi, Sharefah and Alkhereyf, Sakhar and Zaghouani, Wajdi and Khalifa, Salam and AlKhamissi, Badr and Almatham, Rawan and Hamed, Injy and Alyafeai, Zaid and Alowisheq, Areeb and Inoue, Go and Mrini, Khalil and Alshammari, Waad},
     booktitle = {Proceedings of The Third Arabic Natural Language Processing Conference},
     month = nov,
     year = {2025},
     address = {Suzhou, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.arabicnlp-main.21/},
     doi = {10.18653/v1/2025.arabicnlp-main.21},
     pages = {258--277},
     isbn = {979-8-89176-352-4},
   }

9. Overview of the CLEF-2025 CheckThat! Lab: Subjectivity, fact-checking, claim normalization, and retrieval

   Firoj Alam, Julia Maria Struß, Tanmoy Chakraborty , and 8 more authors

   In International Conference of the Cross-Language Evaluation Forum for European Languages , Nov 2025

   Bib

   @inproceedings{alam2025overview,
     title = {Overview of the CLEF-2025 CheckThat! Lab: Subjectivity, fact-checking, claim normalization, and retrieval},
     author = {Alam, Firoj and Stru{\ss}, Julia Maria and Chakraborty, Tanmoy and Dietze, Stefan and Hafid, Salim and Korre, Katerina and Muti, Arianna and Nakov, Preslav and Ruggeri, Federico and Schellhammer, Sebastian and others},
     booktitle = {International Conference of the Cross-Language Evaluation Forum for European Languages},
     pages = {199--223},
     year = {2025},
     organization = {Springer},
   }

10. The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval

    Firoj Alam, Julia Maria Struß, Tanmoy Chakraborty , and 8 more authors

    In European Conference on Information Retrieval , Nov 2025

    Bib

    @inproceedings{alam2025clef,
      title = {The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval},
      author = {Alam, Firoj and Stru{\ss}, Julia Maria and Chakraborty, Tanmoy and Dietze, Stefan and Hafid, Salim and Korre, Katerina and Muti, Arianna and Nakov, Preslav and Ruggeri, Federico and Schellhammer, Sebastian and others},
      booktitle = {European Conference on Information Retrieval},
      pages = {467--478},
      year = {2025},
      organization = {Springer},
    }

11. Working Notes of CLEF 2025 - Conference and Labs of the Evaluation Forum

    Federico Ruggeri, Arianna Muti, Katerina Korre , and 10 more authors

    In Working Notes of CLEF 2025 - Conference and Labs of the Evaluation Forum , Nov 2025
12. Working Notes of CLEF 2025 - Conference and Labs of the Evaluation Forum

    V. Venktesh, Vinay Setty, Avishek Anand , and 6 more authors

    In Working Notes of CLEF 2025 - Conference and Labs of the Evaluation Forum , Nov 2025

13. 

    From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models

    Asim Ersoy, Basel Ahmad Mousi, Shammur Absar Chowdhury , and 3 more authors

    In Proceedings of the 26th Interspeech Conference (Interspeech 2025) , Aug 2025

    Bib

    @inproceedings{ersoy2025fromwords,
      title = {From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models},
      author = {Ersoy, Asim and Mousi, Basel Ahmad and Chowdhury, Shammur Absar and Alam, Firoj and Dalvi, Fahim I and Durrani, Nadir},
      booktitle = {Proceedings of the 26th Interspeech Conference (Interspeech 2025)},
      year = {2025},
      address = {Rotterdam, The Netherlands},
      month = aug,
      organization = {ISCA},
    }

14. 

    SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs

    Firoj Alam, Md Arid Hasan, and Shammur Absar Chowdhury

    In Proceedings of the 26th Interspeech Conference (Interspeech 2025) , Aug 2025

    Bib

    @inproceedings{alam2025spokennativqa,
      title = {{SpokenNativQA}: Multilingual Everyday Spoken Queries for LLMs},
      author = {Alam, Firoj and Hasan, Md Arid and Chowdhury, Shammur Absar},
      booktitle = {Proceedings of the 26th Interspeech Conference (Interspeech 2025)},
      year = {2025},
      address = {Rotterdam, The Netherlands},
      month = aug,
      organization = {ISCA},
    }

15. 

    The Landscape of Arabic Large Language Models

    Shahad Al-Khalifa, Nadir Durrani, Hend Al-Khalifa , and 1 more author

    Communications of the ACM, Aug 2025

    Bib

    @article{al2025landscape,
      title = {The Landscape of Arabic Large Language Models},
      author = {Al-Khalifa, Shahad and Durrani, Nadir and Al-Khalifa, Hend and Alam, Firoj},
      journal = {Communications of the ACM},
      volume = {68},
      number = {10},
      pages = {54--61},
      year = {2025},
      publisher = {ACM New York, NY, USA},
    }

16. Combating Misinformation in the Arab World: Challenges and Opportunities

    Azza Abouzied, Firoj Alam, Raian Ali , and 1 more author

    Communications of the ACM, Aug 2025

    Bib

    @article{abouzied2025combating,
      title = {Combating Misinformation in the Arab World: Challenges and Opportunities},
      author = {Abouzied, Azza and Alam, Firoj and Ali, Raian and Papotti, Paolo},
      journal = {Communications of the ACM},
      volume = {68},
      number = {10},
      pages = {48--53},
      year = {2025},
      publisher = {ACM New York, NY, USA},
    }

17. 

    NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge

    Firoj Alam, Md Arid Hasan, Sahinur Rahman Laskar , and 2 more authors

    arXiv preprint arXiv:2504.05995, Aug 2025

    Bib

    @article{alam2025nativqaframeworkenablingllms,
      title = {{NativQA Framework}: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge },
      author = {Alam, Firoj and Hasan, Md Arid and Laskar, Sahinur Rahman and Kutlu, Mucahid and Chowdhury, Shammur Absar},
      journal = {arXiv preprint arXiv:2504.05995},
      year = {2025},
      url = {https://arxiv.org/abs/2504.05995},
    }

18. 

    PropXplain: Can LLMs Enable Explainable Propaganda Detection?

    Maram Hasanain, Md Arid Hasan, Mohamed Bayan Kmainasi , and 4 more authors

    In Findings of the Association for Computational Linguistics: EMNLP 2025 , Nov 2025

    Bib

    @inproceedings{hasanain-etal-2025-propxplain,
      title = {{P}rop{X}plain: Can {LLM}s Enable Explainable Propaganda Detection?},
      author = {Hasanain, Maram and Hasan, Md Arid and Kmainasi, Mohamed Bayan and Sartori, Elisa and Shahroor, Ali Ezzat and Da San Martino, Giovanni and Alam, Firoj},
      editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
      booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025},
      month = nov,
      year = {2025},
      address = {Suzhou, China},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2025.findings-emnlp.1296/},
      doi = {10.18653/v1/2025.findings-emnlp.1296},
      pages = {23855--23863},
      isbn = {979-8-89176-335-7},
    }

19. 

    MemeIntel: Explainable Detection of Propagandistic and Hateful Memes

    Mohamed Bayan Kmainasi, Abul Hasnat, Md Arid Hasan , and 2 more authors

    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , Nov 2025

    Bib

    @inproceedings{kmainasi-etal-2025-memeintel,
      title = {{M}eme{I}ntel: Explainable Detection of Propagandistic and Hateful Memes},
      author = {Kmainasi, Mohamed Bayan and Hasnat, Abul and Hasan, Md Arid and Shahroor, Ali Ezzat and Alam, Firoj},
      editor = {Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet},
      booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
      month = nov,
      year = {2025},
      address = {Suzhou, China},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2025.emnlp-main.1539/},
      doi = {10.18653/v1/2025.emnlp-main.1539},
      pages = {30251--30267},
      isbn = {979-8-89176-332-6},
    }

20. 

    TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking

    Shahriar Kabir Nahin, Rabindra Nath Nandi, Sagor Sarker , and 7 more authors

    arXiv preprint arXiv:2502.11187, Nov 2025

    Bib

    @article{nahin2025titullms,
      title = {{TituLLMs}: A Family of Bangla LLMs with Comprehensive Benchmarking},
      author = {Nahin, Shahriar Kabir and Nandi, Rabindra Nath and Sarker, Sagor and Muhtaseem, Quazi Sarwar and Kowsher, Md and Shill, Apu Chandraw and Ibrahim, Md and Menon, Mehadi Hasan and Muntasir, Tareq Al and Alam, Firoj},
      journal = {arXiv preprint arXiv:2502.11187},
      year = {2025},
    }

21. 

    NativQA: Multilingual Culturally-Aligned Natural Query for LLMs

    Md. Arid Hasan, Maram Hasanain, Fatema Ahmad , and 6 more authors

    In Findings of the Association for Computational Linguistics: ACL 2025 , Jul 2025
22. The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval

    Firoj Alam, Julia Maria Struß, Tanmoy Chakraborty , and 11 more authors

    In Advances in Information Retrieval , Jul 2025

    Abs Bib

    The CheckThat! lab aims to advance the development of innovative technologies designed to identify and to counteract online disinformation and manipulation efforts across various languages and platforms. The first five editions of the CheckThat! lab focused on the main tasks of the information verification pipeline: check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, the lab has broadened the focus and addressed new problems on auxiliary tasks supporting research and decision-making during the verification process. In the 2025 edition of the lab, we consider tasks at the core of the verification pipeline again as well as auxiliary tasks: Task 1 is on identification of subjectivity (a follow up of the CheckThat! 2024 edition), Task 2 is on claim normalization, Task 3 addresses fact-checking numerical claims, and Task 4 focuses on scientific web discourse processing. These tasks represent challenging classification and retrieval problems at the document and at the span level, including multilingual settings.

    @inproceedings{10.1007/978-3-031-88720-8_68,
      author = {Alam, Firoj and Stru{\ss}, Julia Maria and Chakraborty, Tanmoy and Dietze, Stefan and Hafid, Salim and Korre, Katerina and Muti, Arianna and Nakov, Preslav and Ruggeri, Federico and Schellhammer, Sebastian and Setty, Vinay and Sundriyal, Megha and Todorov, Konstantin and V., Venktesh},
      editor = {Hauff, Claudia and Macdonald, Craig and Jannach, Dietmar and Kazai, Gabriella and Nardini, Franco Maria and Pinelli, Fabio and Silvestri, Fabrizio and Tonellotto, Nicola},
      title = {The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval},
      booktitle = {Advances in Information Retrieval},
      year = {2025},
      publisher = {Springer Nature Switzerland},
      address = {Cham},
      pages = {467--478},
      isbn = {978-3-031-88720-8},
    }

23. BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting

    Mohammad Jahid Ibna Basher, Md Kowsher, Md Saiful Islam , and 8 more authors

    In Findings of the Association for Computational Linguistics: NAACL 2025 , Apr 2025

    Abs

    This paper introduces BnTTS (Bangla Text-To-Speech), the first framework for Bangla speaker adaptation-based TTS, designed to bridge the gap in Bangla speech synthesis using minimal training data. Building upon the XTTS architecture, our approach integrates Bangla into a multilingual TTS pipeline, with modifications to account for the phonetic and linguistic characteristics of the language. We pretrain BnTTS on 3.85k hours of Bangla speech dataset with corresponding text labels and evaluate performance in both zero-shot and few-shot settings on our proposed test dataset. Empirical evaluations in few-shot settings show that BnTTS significantly improves the naturalness, intelligibility, and speaker fidelity of synthesized Bangla speech. Compared to state-of-the-art Bangla TTS systems, BnTTS exhibits superior performance in Subjective Mean Opinion Score (SMOS), Naturalness, and Clarity metrics.

24. 

    LlamaLens: Specialized Multilingual LLM for Analyzing News and Social Media Content

    Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Maram Hasanain , and 3 more authors

    In Findings of the Association for Computational Linguistics: NAACL 2025 , Apr 2025

    Abs Bib

    Large Language Models (LLMs) have demonstrated remarkable success as general-purpose task solvers across various fields. However, their capabilities remain limited when addressing domain-specific problems, particularly in downstream NLP tasks. Research has shown that models fine-tuned on instruction-based downstream NLP datasets outperform those that are not fine-tuned. While most efforts in this area have primarily focused on resource-rich languages like English and broad domains, little attention has been given to multilingual settings and specific domains. To address this gap, this study focuses on developing a specialized LLM, LlamaLens, for analyzing news and social media content in a multilingual context. To the best of our knowledge, this is the first attempt to tackle both domain specificity and multilinguality, with a particular focus on news and social media. Our experimental setup includes 18 tasks, represented by 52 datasets covering Arabic, English, and Hindi. We demonstrate that LlamaLens outperforms the current state-of-the-art (SOTA) on 23 testing sets, and achieves comparable performance on 8 sets. We make the models and resources publicly available for the research community (https://huggingface.co/QCRI).

    @inproceedings{kmainasi-etal-2025-llamalens,
      title = {{L}lama{L}ens: Specialized Multilingual {LLM} for Analyzing News and Social Media Content},
      author = {Kmainasi, Mohamed Bayan and Shahroor, Ali Ezzat and Hasanain, Maram and Laskar, Sahinur Rahman and Hassan, Naeemul and Alam, Firoj},
      editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
      booktitle = {Findings of the Association for Computational Linguistics: NAACL 2025},
      month = apr,
      year = {2025},
      address = {Albuquerque, New Mexico},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2025.findings-naacl.313/},
      pages = {5627--5649},
      isbn = {979-8-89176-195-7},
    }

25. 

    AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs

    Basel Mousi, Nadir Durrani, Fatema Ahmad , and 6 more authors

    In Proceedings of the 31st International Conference on Computational Linguistics , Jan 2025

    Bib

    @inproceedings{mousi-etal-2025-aradice,
      title = {{A}ra{D}i{CE}: Benchmarks for Dialectal and Cultural Capabilities in {LLM}s},
      author = {Mousi, Basel and Durrani, Nadir and Ahmad, Fatema and Hasan, Md. Arid and Hasanain, Maram and Kabbani, Tameem and Dalvi, Fahim and Chowdhury, Shammur Absar and Alam, Firoj},
      editor = {Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven},
      booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
      month = jan,
      year = {2025},
      address = {Abu Dhabi, UAE},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2025.coling-main.283/},
      pages = {4186--4218},
    }

26. GenAI Content Detection Task 2: AI vs. Human – Academic Essay Authenticity Challenge

    Shammur Absar Chowdhury, Hind Almerekhi, Mucahid Kutlu , and 5 more authors

    In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect) , Jan 2025

    Abs Bib

    This paper presents a comprehensive overview of the first edition of the Academic Essay Authenticity Challenge, organized as part of the GenAI Content Detection shared tasks collocated with COLING 2025. This challenge focuses on detecting machine-generated \textitvs human-authored essays for academic purposes. The task is defined as follows: \textit“Given an essay, identify whether it is generated by a machine or authored by a human.” The challenge involves two languages: English and Arabic. During the evaluation phase, 25 teams submitted systems for English and 21 teams for Arabic, reflecting substantial interest in the task. Finally, five teams submitted system description papers. The majority of submissions utilized fine-tuned transformer-based models, with one team employing Large Language Models (LLMs) such as Llama 2 and Llama 3. This paper outlines the task formulation, details the dataset construction process, and explains the evaluation framework. Additionally, we present a summary of the approaches adopted by participating teams. Nearly all submitted systems outperformed the n-gram-based baseline, with the top-performing systems achieving F1 scores exceeding 0.98 for both languages, indicating significant progress in the detection of machine-generated text.

    @inproceedings{chowdhury-etal-2025-genai,
      title = {{G}en{AI} Content Detection Task 2: {AI} vs. Human {--} Academic Essay Authenticity Challenge},
      author = {Chowdhury, Shammur Absar and Almerekhi, Hind and Kutlu, Mucahid and Kele{\c{s}}, Kaan Efe and Ahmad, Fatema and Mohiuddin, Tasnim and Mikros, George and Alam, Firoj},
      editor = {Alam, Firoj and Nakov, Preslav and Habash, Nizar and Gurevych, Iryna and Chowdhury, Shammur and Shelmanov, Artem and Wang, Yuxia and Artemova, Ekaterina and Kutlu, Mucahid and Mikros, George},
      booktitle = {Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)},
      month = jan,
      year = {2025},
      address = {Abu Dhabi, UAE},
      publisher = {International Conference on Computational Linguistics},
      url = {https://aclanthology.org/2025.genaidetect-1.37/},
      pages = {323--333},
    }

27. GenAI Content Detection Task 3: Cross-Domain Machine Generated Text Detection Challenge

    Liam Dugan, Andrew Zhu, Firoj Alam , and 3 more authors

    In Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect) , Jan 2025

    Abs Bib

    Recently there have been many shared tasks targeting the detection of generated text from Large Language Models (LLMs). However, these shared tasks tend to focus either on cases where text is limited to one particular domain or cases where text can be from many domains, some of which may not be seen during test time. In this shared task, using the newly released RAID benchmark, we aim to answer whether or not models can detect generated text from a large, yet fixed, number of domains and LLMs, all of which are seen during training. Over the course of three months, our task was attempted by 9 teams with 23 detector submissions. We find that multiple participants were able to obtain accuracies of over 99% on machine-generated text from RAID while maintaining a 5% False Positive Rate—suggesting that detectors are able to robustly detect text from many domains and models simultaneously. We discuss potential interpretations of this result and provide directions for future research.

    @inproceedings{dugan-etal-2025-genai,
      title = {{G}en{AI} Content Detection Task 3: Cross-Domain Machine Generated Text Detection Challenge},
      author = {Dugan, Liam and Zhu, Andrew and Alam, Firoj and Nakov, Preslav and Apidianaki, Marianna and Callison-Burch, Chris},
      editor = {Alam, Firoj and Nakov, Preslav and Habash, Nizar and Gurevych, Iryna and Chowdhury, Shammur and Shelmanov, Artem and Wang, Yuxia and Artemova, Ekaterina and Kutlu, Mucahid and Mikros, George},
      booktitle = {Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)},
      month = jan,
      year = {2025},
      address = {Abu Dhabi, UAE},
      publisher = {International Conference on Computational Linguistics},
      url = {https://aclanthology.org/2025.genaidetect-1.45/},
      pages = {377--388},
    }

28. Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)

    Jan 2025

    Bib

    @proceedings{genaidetect-ws-2025-1,
      title = {Proceedings of the 1stWorkshop on GenAI Content Detection (GenAIDetect)},
      editor = {Alam, Firoj and Nakov, Preslav and Habash, Nizar and Gurevych, Iryna and Chowdhury, Shammur and Shelmanov, Artem and Wang, Yuxia and Artemova, Ekaterina and Kutlu, Mucahid and Mikros, George},
      month = jan,
      year = {2025},
      address = {Abu Dhabi, UAE},
      publisher = {International Conference on Computational Linguistics},
      url = {https://aclanthology.org/2025.genaidetect-1.0/},
    }

2024

1. 

   Native vs non-native language prompting: A comparative analysis

   Mohamed Bayan Kmainasi, Rakif Khan, Ali Ezzat Shahroor , and 3 more authors

   In International Conference on Web Information Systems Engineering , Jan 2024

   Bib

   @inproceedings{kmainasi2024native,
     title = {Native vs non-native language prompting: A comparative analysis},
     author = {Kmainasi, Mohamed Bayan and Khan, Rakif and Shahroor, Ali Ezzat and Bendou, Boushra and Hasanain, Maram and Alam, Firoj},
     booktitle = {International Conference on Web Information Systems Engineering},
     pages = {406--420},
     year = {2024},
     organization = {Springer},
   }

2. 

   Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-agent LLMs

   Firoj Alam, Md Rafiul Biswas, Uzair Shah , and 2 more authors

   In International Conference on Web Information Systems Engineering , Jan 2024

   Bib

   @inproceedings{alam2024propaganda,
     title = {Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-agent LLMs},
     author = {Alam, Firoj and Biswas, Md Rafiul and Shah, Uzair and Zaghouani, Wajdi and Mikros, Georgios},
     booktitle = {International Conference on Web Information Systems Engineering},
     pages = {380--390},
     year = {2024},
     organization = {Springer},
   }

3. 

   ArMeme: Propagandistic Content in Arabic Memes

   Firoj Alam, Abul Hasnat, Fatema Ahmad , and 2 more authors

   In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , Nov 2024

   Abs Bib

   With the rise of digital communication memes have become a significant medium for cultural and political expression that is often used to mislead audience. Identification of such misleading and persuasive multimodal content become more important among various stakeholders, including social media platforms, policymakers, and the broader society as they often cause harm to the individuals, organizations and/or society. While there has been effort to develop AI based automatic system for resource rich languages (e.g., English), it is relatively little to none for medium to low resource languages. In this study, we focused on developing an Arabic memes dataset with manual annotations of propagandistic content. We annotated \sim6K Arabic memes collected from various social media platforms, which is a first resource for Arabic multimodal research. We provide a comprehensive analysis aiming to develop computational tools for their detection. We made the dataset publicly available for the community.

   @inproceedings{alam-etal-2024-armeme,
     title = {{A}r{M}eme: Propagandistic Content in {A}rabic Memes},
     author = {Alam, Firoj and Hasnat, Abul and Ahmad, Fatema and Hasan, Md. Arid and Hasanain, Maram},
     editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
     booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
     month = nov,
     year = {2024},
     address = {Miami, Florida, USA},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.emnlp-main.1173},
     pages = {21071--21090},
   }

4. 

   ArAIEval Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal Arabic Content

   Maram Hasanain, Md. Arid Hasan, Fatema Ahmad , and 4 more authors

   In Proceedings of The Second Arabic Natural Language Processing Conference , Aug 2024

   Abs Bib

   We present an overview of the second edition of the ArAIEval shared task, organized as part of the ArabicNLP 2024 conference co-located with ACL 2024. In this edition, ArAIEval offers two tasks: (i) detection of propagandistic textual spans with persuasion techniques identification in tweets and news articles, and (ii) distinguishing between propagandistic and non-propagandistic memes. A total of 14 teams participated in the final evaluation phase, with 6 and 9 teams participating in Tasks 1 and 2, respectively. Finally, 11 teams submitted system description papers. Across both tasks, we observed that fine-tuning transformer models such as AraBERT was at the core of the majority of the participating systems. We provide a description of the task setup, including a description of the dataset construction and the evaluation setup. We further provide a brief overview of the participating systems. All datasets and evaluation scripts are released to the research community. We hope this will enable further research on these important tasks in Arabic.

   @inproceedings{hasanain-etal-2024-araieval,
     title = {{A}r{AIE}val Shared Task: Propagandistic Techniques Detection in Unimodal and Multimodal {A}rabic Content},
     author = {Hasanain, Maram and Hasan, Md. Arid and Ahmad, Fatema and Suwaileh, Reem and Biswas, Md. Rafiul and Zaghouani, Wajdi and Alam, Firoj},
     editor = {Habash, Nizar and Bouamor, Houda and Eskander, Ramy and Tomeh, Nadi and Abu Farha, Ibrahim and Abdelali, Ahmed and Touileb, Samia and Hamed, Injy and Onaizan, Yaser and Alhafni, Bashar and Antoun, Wissam and Khalifa, Salam and Haddad, Hatem and Zitouni, Imed and AlKhamissi, Badr and Almatham, Rawan and Mrini, Khalil},
     booktitle = {Proceedings of The Second Arabic Natural Language Processing Conference},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.arabicnlp-1.44},
     pages = {456--466},
   }

5. 

   The CLEF-2024 CheckThat! Lab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities, and Adversarial Robustness

   Alberto Barrón-Cedeño, Firoj Alam, Tanmoy Chakraborty , and 9 more authors

   In Advances in Information Retrieval , Aug 2024

   Abs Bib

   The first five editions of the CheckThat! lab focused on the main tasks of the information verification pipeline: check-worthiness, evidence retrieval and pairing, and verification. Since the 2023 edition, it has been focusing on new problems that can support the research and decision making during the verification process. In this new edition, we focus on new problems and —for the first time— we propose six tasks in fifteen languages (Arabic, Bulgarian, English, Dutch, French, Georgian, German, Greek, Italian, Polish, Portuguese, Russian, Slovene, Spanish, and code-mixed Hindi-English): Task 1 estimation of check-worthiness (the only task that has been present in all CheckThat! editions), Task 2 identification of subjectivity (a follow up of CheckThat! 2023 edition), Task 3 identification of persuasion (a follow up of SemEval 2023), Task 4 detection of hero, villain, and victim from memes (a follow up of CONSTRAINT 2022), Task 5 Rumor Verification using Evidence from Authorities (a first), and Task 6 robustness of credibility assessment with adversarial examples (a first). These tasks represent challenging classification and retrieval problems at the document and at the span level, including multilingual and multimodal settings.

   @inproceedings{CheckThat:ECIR2024,
     author = {Barr{\'o}n-Cede{\~{n}}o, Alberto and Alam, Firoj and Chakraborty, Tanmoy and Elsayed, Tamer and Nakov, Preslav and Przyby{\l}a, Piotr and Stru{\ss}, Julia Maria and Haouari, Fatima and Hasanain, Maram and Ruggeri, Federico and Song, Xingyi and Suwaileh, Reem},
     editor = {Goharian, Nazli and Tonellotto, Nicola and He, Yulan and Lipani, Aldo and McDonald, Graham and Macdonald, Craig and Ounis, Iadh},
     title = {The {CLEF}-2024 {C}heck{T}hat! {L}ab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities, and Adversarial Robustness},
     booktitle = {Advances in Information Retrieval},
     year = {2024},
     publisher = {Springer Nature Switzerland},
     noaddress = {Cham},
     pages = {449--458},
     isbn = {978-3-031-56069-9},
   }

6. Overview of the CLEF-2024 CheckThat! Lab: Check-Worthiness, Subjectivity, Persuasion, Roles, Authorities and Adversarial Robustness

   Alberto Barrón-Cedeño, Firoj Alam, Julia Maria Struß , and 12 more authors

   In Experimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings of the Fifteenth International Conference of the CLEF Association (CLEF 2024) , Aug 2024

   Bib

   @inproceedings{clef-checkthat:2024-lncs,
     author = {Barr{\'o}n-Cede{\~{n}}o, Alberto and Alam, Firoj and Stru{\ss}, Julia Maria and Nakov, Preslav and Chakraborty, Tanmoy and Elsayed, Tamer and Przybyła, Piotr and Caselli, Tommaso and Da San Martino, Giovanni and Haouari, Fatima and Li, Chengkai and Piskorski, Jakub and Ruggeri, Federico and Song, Xingyi and Suwaileh, Reem},
     title = {Overview of the {CLEF}-2024 {CheckThat! Lab}: Check-Worthiness, Subjectivity, Persuasion, Roles,
     Authorities and Adversarial Robustness},
     editor = {Goeuriot, Lorraine and Mulhem, Philippe and Quénot, Georges and Schwab, Didier and Soulier, Laure and Di Nunzio, Giorgio Maria and Galuščáková, Petra and García Seco de Herrera, Alba and Faggioli, Guglielmo and Ferro, Nicola},
     booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction.
     Proceedings of the Fifteenth International Conference of the CLEF Association (CLEF 2024)},
     year = {2024},
   }

7. Overview of the CLEF-2024 CheckThat! Lab Task 1 on Check-Worthiness Estimation of Multigenre Content

   Maram Hasanain, Reem Suwaileh, Sanne Weering , and 6 more authors

   In Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum , Aug 2024

   Bib

   @inproceedings{clef-checkthat:2024:task1,
     author = {Hasanain, Maram and Suwaileh, Reem and Weering, Sanne and Li, Chengkai and Caselli, Tommaso and Zaghouani, Wajdi and Barr\'{o}n-Cede\~{n}o, Alberto and Nakov, Preslav and Alam, Firoj},
     title = {Overview of the {CLEF}-2024 {CheckThat}! Lab Task 1 on Check-Worthiness Estimation of Multigenre Content},
     booktitle = {Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum},
     series = {CLEF~2024},
     address = {Grenoble, France},
     year = {2024},
   }

8. Overview of the CLEF-2024 CheckThat! Lab Task 2 on Subjectivity in News Articles

   Julia Maria Struß, Federico Ruggeri, Alberto Barrón-Cedeño , and 11 more authors

   In Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum , Aug 2024

   Bib

   @inproceedings{clef-checkthat:2024:task2,
     author = {Stru\ss, Julia Maria and Ruggeri, Federico and Barr\'on-Cede\~no, Alberto and Alam, Firoj and Dimitrov, Dimitar and Galassi, Andrea and Pachov, Georgi and Koychev, Ivan and Nakov, Preslav and Siegel, Melanie and Wiegand, Michael and Hasanain, Maram and Suwaileh, Reem and Zaghouani, Wajdi},
     title = {Overview of the {CLEF}-2024 {CheckThat}! Lab Task 2 on Subjectivity in News Articles},
     booktitle = {Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum},
     series = {CLEF~2024},
     address = {Grenoble, France},
     year = {2024},
   }

9. Overview of the CLEF-2024 CheckThat! Lab Task 3 on Persuasion Techniques

   Jakub Piskorski, Nicolas Stefanovitch, Firoj Alam , and 16 more authors

   In Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum , Aug 2024

   Bib

   @inproceedings{clef-checkthat:2024:task3,
     title = {Overview of the {CLEF-2024 CheckThat!} Lab Task 3 on Persuasion Techniques},
     author = {Piskorski, Jakub and Stefanovitch, Nicolas and Alam, Firoj and Campos, Ricardo and Dimitrov, Dimitar and Jorge, Al{\'\i}pio and Pollak, Senja and Ribin, Nikolay and Fijav{\v{z}}, Zoran and Hasanain, Maram and Guimar{\~a}es, Nuno and Pacheco, Ana Filipa and Sartori, Elisa and Silvano, Purifica{\c{c}}{\~a}o and Zwitter, Ana Vitez and Koychev, Ivan and Yu, Nana and Nakov, Preslav and Da San Martino, Giovanni},
     booktitle = {Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum},
     series = {CLEF~2024},
     address = {Grenoble, France},
     year = {2024},
   }

10. 

    SemEval-2024 Task 4: Multilingual Detection of Persuasion Techniques in Memes

    Dimitar Dimitrov, Firoj Alam, Maram Hasanain , and 4 more authors

    In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024) , Jun 2024

    Bib

    @inproceedings{dimitrov-etal-2024-semeval,
      address = {Mexico City, Mexico},
      author = {Dimitrov, Dimitar and Alam, Firoj and Hasanain, Maram and Hasnat, Abul and Silvestri, Fabrizio and Nakov, Preslav and Da San Martino, Giovanni},
      booktitle = {Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Ojha, Atul Kr. and Do{\u{g}}ru{\"o}z, A. Seza and Tayyar Madabushi, Harish and Da San Martino, Giovanni and Rosenthal, Sara and Ros{\'a}, Aiala},
      month = jun,
      pages = {2009--2026},
      publisher = {Association for Computational Linguistics},
      title = {{S}em{E}val-2024 Task 4: Multilingual Detection of Persuasion Techniques in Memes},
      year = {2024},
      url = {https://aclanthology.org/2024.semeval-1.275},
      doi = {https://doi.org/10.18653/v1/2024.semeval-1.275},
    }

11. 

    Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles

    Maram Hasanain, Fatema Ahmad, and Firoj Alam

    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , May 2024

    Bib

    @inproceedings{hasanain-etal-2024-gpt,
      address = {Torino, Italia},
      author = {Hasanain, Maram and Ahmad, Fatema and Alam, Firoj},
      booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
      month = may,
      pages = {2724--2744},
      publisher = {ELRA and ICCL},
      title = {Can {GPT}-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles},
      year = {2024},
      url = {https://aclanthology.org/2024.lrec-main.244},
    }

12. Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis

    Md. Arid Hasan, Shudipta Das, Afiyat Anjum , and 4 more authors

    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , May 2024

    Bib

    @inproceedings{hasan-etal-2024-zero,
      address = {Torino, Italia},
      author = {Hasan, Md. Arid and Das, Shudipta and Anjum, Afiyat and Alam, Firoj and Anjum, Anika and Sarker, Avijit and Noori, Sheak Rashed Haider},
      booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
      month = may,
      pages = {17808--17818},
      publisher = {ELRA and ICCL},
      title = {Zero- and Few-Shot Prompting with {LLM}s: A Comparative Study with Fine-tuned Models for {B}angla Sentiment Analysis},
      year = {2024},
      url = {https://aclanthology.org/2024.lrec-main.1549},
    }

13. 

    LLMs for Low Resource Languages in Multilingual, Multimodal and Dialectal Settings

    Firoj Alam, Shammur Absar Chowdhury, Sabri Boughorbel , and 1 more author

    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts , Mar 2024

    Bib

    @inproceedings{alam-etal-2024-llms,
      address = {St. Julian{'}s, Malta},
      author = {Alam, Firoj and Chowdhury, Shammur Absar and Boughorbel, Sabri and Hasanain, Maram},
      booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Tutorial Abstracts},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Mesgar, Mohsen and Lo{\'a}iciga, Sharid},
      month = mar,
      pages = {27--33},
      publisher = {Association for Computational Linguistics},
      title = {{LLM}s for Low Resource Languages in Multilingual, Multimodal and Dialectal Settings},
      year = {2024},
      url = {https://aclanthology.org/2024.eacl-tutorials.5},
    }

14. 

    LAraBench: Benchmarking Arabic AI with Large Language Models

    Ahmed Abdelali, Hamdy Mubarak, Shammur Chowdhury , and 14 more authors

    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) , Mar 2024

    Abs Bib

    Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored to particular languages and tasks. LAraBench addresses this gap for Arabic Natural Language Processing (NLP) and Speech Processing tasks, including sequence tagging and content classification across different domains. We utilized models such as GPT-3.5-turbo, GPT-4, BLOOMZ, Jais-13b-chat, Whisper, and USM, employing zero and few-shot learning techniques to tackle 33 distinct tasks across 61 publicly available datasets. This involved 98 experimental setups, encompassing ~296K data points, ~46 hours of speech, and 30 sentences for Text-to-Speech (TTS). This effort resulted in 330+ sets of experiments. Our analysis focused on measuring the performance gap between SOTA models and LLMs. The overarching trend observed was that SOTA models generally outperformed LLMs in zero-shot learning, with a few exceptions. Notably, larger computational models with few-shot learning techniques managed to reduce these performance gaps. Our findings provide valuable insights into the applicability of LLMs for Arabic NLP and speech processing tasks.

    @inproceedings{abdelali-etal-2024-larabench,
      address = {St. Julian{'}s, Malta},
      author = {Abdelali, Ahmed and Mubarak, Hamdy and Chowdhury, Shammur and Hasanain, Maram and Mousi, Basel and Boughorbel, Sabri and Abdaljalil, Samir and El Kheir, Yassine and Izham, Daniel and Dalvi, Fahim and Hawasly, Majd and Nazar, Nizi and Elshahawy, Youssef and Ali, Ahmed and Durrani, Nadir and Milic-Frayling, Natasa and Alam, Firoj},
      booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Graham, Yvette and Purver, Matthew},
      month = mar,
      pages = {487--520},
      publisher = {Association for Computational Linguistics},
      title = {{LA}ra{B}ench: Benchmarking {A}rabic {AI} with Large Language Models},
      year = {2024},
      url = {https://aclanthology.org/2024.eacl-long.30},
    }

15. 

    LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking

    Fahim Dalvi, Maram Hasanain, Sabri Boughorbel , and 10 more authors

    In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations , Mar 2024

    Abs Bib

    The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online (https://youtu.be/9cC2m_abk3A).

    @inproceedings{dalvi-etal-2024-llmebench,
      address = {St. Julians, Malta},
      author = {Dalvi, Fahim and Hasanain, Maram and Boughorbel, Sabri and Mousi, Basel and Abdaljalil, Samir and Nazar, Nizi and Abdelali, Ahmed and Chowdhury, Shammur Absar and Mubarak, Hamdy and Ali, Ahmed and Hawasly, Majd and Durrani, Nadir and Alam, Firoj},
      booktitle = {Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Aletras, Nikolaos and De Clercq, Orphee},
      month = mar,
      pages = {214--222},
      publisher = {Association for Computational Linguistics},
      title = {{LLM}e{B}ench: A Flexible Framework for Accelerating {LLM}s Benchmarking},
      year = {2024},
      url = {https://aclanthology.org/2024.eacl-demo.23},
    }

16. 

    Large Language Models for Propaganda Span Annotation

    Maram Hasanain, Fatema Ahmad, and Firoj Alam

    In Findings of the Association for Computational Linguistics: EMNLP 2024 , Nov 2024

    Abs Bib

    The use of propagandistic techniques in online content has increased in recent years aiming to manipulate online audiences. Fine-grained propaganda detection and extraction of textual spans where propaganda techniques are used, are essential for more informed content consumption. Automatic systems targeting the task over lower resourced languages are limited, usually obstructed by lack of large scale training datasets. Our study investigates whether Large Language Models (LLMs), such as GPT-4, can effectively extract propagandistic spans. We further study the potential of employing the model to collect more cost-effective annotations. Finally, we examine the effectiveness of labels provided by GPT-4 in training smaller language models for the task. The experiments are performed over a large-scale in-house manually annotated dataset. The results suggest that providing more annotation context to GPT-4 within prompts improves its performance compared to human annotators. Moreover, when serving as an expert annotator (consolidator), the model provides labels that have higher agreement with expert annotators, and lead to specialized models that achieve state-of-the-art over an unseen Arabic testing set. Finally, our work is the first to show the potential of utilizing LLMs to develop annotated datasets for propagandistic spans detection task prompting it with annotations from human annotators with limited expertise. All scripts and annotations will be shared with the community.

    @inproceedings{hasanain-etal-2024-large,
      title = {Large Language Models for Propaganda Span Annotation},
      author = {Hasanain, Maram and Ahmad, Fatema and Alam, Firoj},
      editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
      booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
      month = nov,
      year = {2024},
      address = {Miami, Florida, USA},
      publisher = {Association for Computational Linguistics},
      url = {https://aclanthology.org/2024.findings-emnlp.850},
      pages = {14522--14532},
    }

2023

1. BLP-2023 Task 2: Sentiment Analysis

   Md. Arid Hasan, Firoj Alam, Anika Anjum , and 2 more authors

   In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023) , Dec 2023

   Bib

   @inproceedings{hasan-etal-2023-blp,
     address = {Singapore},
     author = {Hasan, Md. Arid and Alam, Firoj and Anjum, Anika and Das, Shudipta and Anjum, Afiyat},
     booktitle = {Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)},
     date-modified = {2024-08-03 12:11:55 +0300},
     editor = {Alam, Firoj and Kar, Sudipta and Chowdhury, Shammur Absar and Sadeque, Farig and Amin, Ruhul},
     month = dec,
     pages = {354--364},
     publisher = {Association for Computational Linguistics},
     title = {{BLP}-2023 Task 2: Sentiment Analysis},
     year = {2023},
     url = {https://aclanthology.org/2023.banglalp-1.48},
     doi = {https://doi.org/10.18653/v1/2023.banglalp-1.48},
   }

2. Detecting and identifying the reasons for deleted tweets before they are posted

   Hamdy Mubarak, Samir Abdaljalil, Azza Nassar , and 1 more author

   Frontiers in Artificial Intelligence, Dec 2023

   Bib

   @article{mubarak2023detecting,
     author = {Mubarak, Hamdy and Abdaljalil, Samir and Nassar, Azza and Alam, Firoj},
     journal = {Frontiers in Artificial Intelligence},
     pages = {1219767},
     publisher = {Frontiers Media SA},
     title = {Detecting and identifying the reasons for deleted tweets before they are posted},
     volume = {6},
     year = {2023},
   }

3. Overview of the CLEF–2023 CheckThat! Lab on Checkworthiness, Subjectivity, Political Bias, Factuality, and Authority of News Articles and Their Source

   Alberto Barrón-Cedeño, Firoj Alam, Andrea Galassi , and 8 more authors

   In International Conference of the Cross-Language Evaluation Forum for European Languages , Dec 2023

   Bib

   @inproceedings{barron2023overview,
     author = {Barr{\'o}n-Cede{\~n}o, Alberto and Alam, Firoj and Galassi, Andrea and Da San Martino, Giovanni and Nakov, Preslav and Elsayed, Tamer and Azizov, Dilshod and Caselli, Tommaso and Cheema, Gullal S and Haouari, Fatima and others},
     booktitle = {International Conference of the Cross-Language Evaluation Forum for European Languages},
     organization = {Springer},
     pages = {251--275},
     title = {Overview of the CLEF--2023 CheckThat! Lab on Checkworthiness, Subjectivity, Political Bias, Factuality, and Authority of News Articles and Their Source},
     year = {2023},
   }

4. 

   ConceptX: A framework for latent concept analysis

   Firoj Alam, Fahim Dalvi, Nadir Durrani , and 3 more authors

   In Proceedings of the AAAI Conference on Artificial Intelligence , Dec 2023

   Bib

   @inproceedings{alam2023conceptx,
     author = {Alam, Firoj and Dalvi, Fahim and Durrani, Nadir and Sajjad, Hassan and Khan, Abdul Rafae and Xu, Jia},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     number = {13},
     pages = {16395--16397},
     title = {{ConceptX}: A framework for latent concept analysis},
     volume = {37},
     year = {2023},
   }

5. Overview of the CLEF-2023 CheckThat! Lab Task 2 on Subjectivity in News Articles

   Andrea Galassi, Federico Ruggeri, Alberto Barrón-Cedeño , and 14 more authors

   In , Dec 2023

   Bib

   @inproceedings{clef-checkthat:2023:task2,
     author = {Galassi, Andrea and Ruggeri, Federico and Barr\'{o}n-Cede\~{n}o, Alberto and Alam, Firoj and Caselli, Tommaso and Kutlu, Mucahid and Struss, {Julia Maria} and Antici, Francesco and Hasanain, Maram and K{\"o}hler, Juliane and Korre, Katerina and Leistra, Folkert and Muti, Arianna and Siegel, Melanie and {Mehmet Deniz}, Turkmen. and Wiegand, Michael and Zaghouani, Wajdi},
     crossref = {clef2023-workingnotes},
     date-modified = {2024-08-03 12:29:30 +0300},
     title = {Overview of the {CLEF}-2023 {CheckThat}! Lab Task 2 on Subjectivity in News Articles},
     year = {2023},
   }

6. Overview of the CLEF-2023 CheckThat! Lab Task 3 on Political Bias of News Articles and News Media

   Giovanni Da San Martino, Firoj Alam, Maram Hasanain , and 3 more authors

   In Working Notes of CLEF 2023 - Conference and Labs of the Evaluation Forum , Dec 2023

   Bib

   @inproceedings{clef-checkthat:2023:task3,
     author = {Da San Martino, Giovanni and Alam, Firoj and Hasanain, Maram and Nandi, Rabindra Nath and Azizov, Dilshod and Nakov, Preslav},
     booktitle = {Working Notes of {CLEF} 2023 - Conference and Labs of the Evaluation Forum},
     crossref = {clef2023-workingnotes},
     date-modified = {2024-08-03 12:30:07 +0300},
     title = {Overview of the {CLEF}-2023 {CheckThat}! Lab Task 3 on Political Bias of News Articles and News Media},
     year = {2023},
   }

7. The clef-2023 checkthat! lab: Checkworthiness, subjectivity, political bias, factuality, and authority

   Alberto Barrón-Cedeño, Firoj Alam, Tommaso Caselli , and 8 more authors

   In European Conference on Information Retrieval , Dec 2023

   Bib

   @inproceedings{barron2023clef,
     author = {Barr{\'o}n-Cede{\~n}o, Alberto and Alam, Firoj and Caselli, Tommaso and Da San Martino, Giovanni and Elsayed, Tamer and Galassi, Andrea and Haouari, Fatima and Ruggeri, Federico and Stru{\ss}, Julia Maria and Nandi, Rabindra Nath and others},
     booktitle = {European Conference on Information Retrieval},
     organization = {Springer},
     pages = {506--517},
     title = {The clef-2023 checkthat! lab: Checkworthiness, subjectivity, political bias, factuality, and authority},
     year = {2023},
   }

8. 

   Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognition

   Rabindra Nath Nandi, Mehadi Menon, Tareq Muntasir , and 5 more authors

   In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023) , Dec 2023

   Abs Bib

   One of the major challenges for developing automatic speech recognition (ASR) for low-resource languages is the limited access to labeled data with domain-specific variations. In this study, we propose a pseudo-labeling approach to develop a large-scale domain-agnostic ASR dataset. With the proposed methodology, we developed a 20k+ hours labeled Bangla speech dataset covering diverse topics, speaking styles, dialects, noisy environments, and conversational scenarios. We then exploited the developed corpus to design a conformer-based ASR system. We benchmarked the trained ASR with publicly available datasets and compared it with other available models. To investigate the efficacy, we designed and developed a human-annotated domain-agnostic test set composed of news, telephony, and conversational data among others. Our results demonstrate the efficacy of the model trained on psuedo-label data for the designed test-set along with publicly-available Bangla datasets. The experimental resources will be publicly available.https://github.com/hishab-nlp/Pseudo-Labeling-for-Domain-Agnostic-Bangla-ASR

   @inproceedings{nandi-etal-2023-pseudo,
     address = {Singapore},
     author = {Nandi, Rabindra Nath and Menon, Mehadi and Muntasir, Tareq and Sarker, Sagor and Muhtaseem, Quazi Sarwar and Islam, Md. Tariqul and Chowdhury, Shammur and Alam, Firoj},
     booktitle = {Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)},
     date-modified = {2024-08-03 12:08:38 +0300},
     editor = {Alam, Firoj and Kar, Sudipta and Chowdhury, Shammur Absar and Sadeque, Farig and Amin, Ruhul},
     month = dec,
     pages = {152--162},
     publisher = {Association for Computational Linguistics},
     title = {Pseudo-Labeling for Domain-Agnostic {B}angla Automatic Speech Recognition},
     year = {2023},
     url = {https://aclanthology.org/2023.banglalp-1.16},
     bdsk-url-2 = {https://doi.org/10.18653/v1/2023.banglalp-1.16},
   }

9. QCRI at SemEval-2023 Task 3: News Genre, Framing and Persuasion Techniques Detection Using Multilingual Models

   Maram Hasanain, Ahmed El-Shangiti, Rabindra Nath Nandi , and 2 more authors

   In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023) , Jul 2023

   Bib

   @inproceedings{hasanain-etal-2023-qcri,
     address = {Toronto, Canada},
     author = {Hasanain, Maram and El-Shangiti, Ahmed and Nandi, Rabindra Nath and Nakov, Preslav and Alam, Firoj},
     booktitle = {Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)},
     date-modified = {2024-08-03 11:44:50 +0300},
     editor = {Ojha, Atul Kr. and Do{\u{g}}ru{\"o}z, A. Seza and Da San Martino, Giovanni and Tayyar Madabushi, Harish and Kumar, Ritesh and Sartori, Elisa},
     month = jul,
     pages = {1237--1244},
     publisher = {Association for Computational Linguistics},
     title = {{QCRI} at {S}em{E}val-2023 Task 3: News Genre, Framing and Persuasion Techniques Detection Using Multilingual Models},
     year = {2023},
     url = {https://aclanthology.org/2023.semeval-1.172},
     bdsk-url-2 = {https://doi.org/10.18653/v1/2023.semeval-1.172},
   }

10. Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)

    Dec 2023

    Bib

    @proceedings{banglalp-2023-bangla,
      address = {Singapore},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Alam, Firoj and Kar, Sudipta and Chowdhury, Shammur Absar and Sadeque, Farig and Amin, Ruhul},
      month = dec,
      publisher = {Association for Computational Linguistics},
      title = {Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)},
      year = {2023},
      url = {https://aclanthology.org/2023.banglalp-1.0},
    }

11. ArAIEval Shared Task: Persuasion Techniques and Disinformation Detection in Arabic Text

    Maram Hasanain, Firoj Alam, Hamdy Mubarak , and 5 more authors

    In Proceedings of ArabicNLP 2023 , Dec 2023

    Bib

    @inproceedings{hasanain-etal-2023-araieval,
      address = {Singapore (Hybrid)},
      author = {Hasanain, Maram and Alam, Firoj and Mubarak, Hamdy and Abdaljalil, Samir and Zaghouani, Wajdi and Nakov, Preslav and Da San Martino, Giovanni and Freihat, Abed},
      booktitle = {Proceedings of ArabicNLP 2023},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Sawaf, Hassan and El-Beltagy, Samhaa and Zaghouani, Wajdi and Magdy, Walid and Abdelali, Ahmed and Tomeh, Nadi and Abu Farha, Ibrahim and Habash, Nizar and Khalifa, Salam and Keleg, Amr and Haddad, Hatem and Zitouni, Imed and Mrini, Khalil and Almatham, Rawan},
      month = dec,
      pages = {483--493},
      publisher = {Association for Computational Linguistics},
      title = {{A}r{AIE}val Shared Task: Persuasion Techniques and Disinformation Detection in {A}rabic Text},
      year = {2023},
      url = {https://aclanthology.org/2023.arabicnlp-1.44},
      bdsk-url-2 = {https://doi.org/10.18653/v1/2023.arabicnlp-1.44},
    }

12. Nexus at ArAIEval Shared Task: Fine-Tuning Arabic Language Models for Propaganda and Disinformation Detection

    Yunze Xiao, and Firoj Alam

    In Proceedings of ArabicNLP 2023 , Dec 2023

    Bib

    @inproceedings{xiao-alam-2023-nexus,
      address = {Singapore (Hybrid)},
      author = {Xiao, Yunze and Alam, Firoj},
      booktitle = {Proceedings of ArabicNLP 2023},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Sawaf, Hassan and El-Beltagy, Samhaa and Zaghouani, Wajdi and Magdy, Walid and Abdelali, Ahmed and Tomeh, Nadi and Abu Farha, Ibrahim and Habash, Nizar and Khalifa, Salam and Keleg, Amr and Haddad, Hatem and Zitouni, Imed and Mrini, Khalil and Almatham, Rawan},
      month = dec,
      pages = {576--582},
      publisher = {Association for Computational Linguistics},
      title = {Nexus at {A}r{AIE}val Shared Task: Fine-Tuning {A}rabic Language Models for Propaganda and Disinformation Detection},
      year = {2023},
      url = {https://aclanthology.org/2023.arabicnlp-1.58},
      bdsk-url-2 = {https://doi.org/10.18653/v1/2023.arabicnlp-1.58},
    }

13. Z-Index at CheckThat!-2023: Unimodal and Multimodal Check-worthiness Classification.

    Prerona Tarannum, Md Arid Hasan, Firoj Alam , and 1 more author

    In CLEF (Working Notes) , Dec 2023

    Bib

    @inproceedings{tarannum2023z,
      author = {Tarannum, Prerona and Hasan, Md Arid and Alam, Firoj and Noori, Sheak Rashed Haider},
      booktitle = {CLEF (Working Notes)},
      pages = {482--493},
      title = {Z-Index at CheckThat!-2023: Unimodal and Multimodal Check-worthiness Classification.},
      year = {2023},
    }

14. Overview of the CLEF–2023 CheckThat! Lab Checkworthiness, Subjectivity, Political Bias, Factuality, and Authority of News Articles and Their Source

    Alberto Barrón-Cedeño, Firoj Alam, Andrea Galassi , and 13 more authors

    In Experimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings of the Fourteenth International Conference of the CLEF Association (CLEF 2023) , Dec 2023

    Bib

    @inproceedings{clef-checkthat:2023,
      author = {Barr{\'o}n-Cede{\~{n}}o, Alberto and Alam, Firoj and Galassi, Andrea and {Da San Martino}, Giovanni and Nakov, Preslav and and Elsayed, Tamer and Azizov, Dilshod and Caselli, Tommaso and Cheema, {Gullal S.} and Haouari, Fatima and Hasanain, Maram and Kutlu, Mucahid and Li, Chengkai and Ruggeri, Federico and Stru{\ss}, Julia Maria and Zaghouani, Wajdi},
      booktitle = {Experimental IR Meets Multilinguality, Multimodality, and Interaction. Proceedings of the Fourteenth International Conference of the CLEF Association ({CLEF} 2023)},
      editor = {Arampatzis, Avi and Kanoulas, Evangelos and Tsikrika, Theodora and Vrochidis, Stefanos and Giachanou, Anastasia and Li, Dan and Aliannejadi, Mohammad and Vlachos, Michalis and Faggioli, Guglielmo and Ferro, Nicola},
      title = {Overview of the {CLEF}--2023 {CheckThat! Lab} Checkworthiness, Subjectivity, Political Bias, Factuality, and Authority of News Articles and Their Source},
      year = {2023},
    }

15. The CLEF-2023 CheckThat! Lab: Checkworthiness, Subjectivity, Political Bias, Factuality, and Authority

    Alberto Barrón-Cedeño, Firoj Alam, Tommaso Caselli , and 10 more authors

    In Advances in Information Retrieval , Dec 2023

    Bib

    @inproceedings{CheckThat:ECIR2023,
      address = {Cham},
      author = {Barr{\'o}n-Cede{\~{n}}o, Alberto and Alam, Firoj and Caselli, Tommaso and Da San Martino, Giovanni and Elsayed, Tamer and Galassi, Andrea and Haouari, Fatima and Ruggeri, Federico and Stru{\ss}, Julia Maria and Nandi, Rabindra Nath and Cheema, Gullal S. and Azizov, Dilshod and Nakov, Preslav},
      booktitle = {Advances in Information Retrieval},
      editor = {Kamps, Jaap and Goeuriot, Lorraine and Crestani, Fabio and Maistro, Maria and Joho, Hideo and Davis, Brian and Gurrin, Cathal and Kruschwitz, Udo and Caputo, Annalina},
      isbn = {978-3-031-28241-6},
      pages = {506--517},
      publisher = {Springer Nature Switzerland},
      title = {The {CLEF}-2023 {CheckThat! Lab}: Checkworthiness, Subjectivity, Political Bias, Factuality, and Authority},
      year = {2023},
    }

16. Overview of the CLEF-2023 CheckThat! Lab Task 1 on Check-Worthiness in Multimodal and Multigenre Content

    Firoj Alam, Alberto Barrón-Cedeño, Gullal S. Cheema , and 8 more authors

    In , Dec 2023

    Bib

    @inproceedings{clef-checkthat:2023:task1,
      author = {Alam, Firoj and Barr\'{o}n-Cede\~{n}o, Alberto and Cheema, Gullal S. and Hakimov, Sherzod and Hasanain, Maram and Li, Chengkai and M\'{\i}guez, Rub\'{e}n and Mubarak, Hamdy and Shahi, Gautam Kishore and Zaghouani, Wajdi and Nakov, Preslav},
      crossref = {clef2023-workingnotes},
      date-modified = {2024-08-03 12:29:01 +0300},
      title = {Overview of the {CLEF}-2023 {CheckThat}! Lab Task 1 on Check-Worthiness in Multimodal and Multigenre Content},
      year = {2023},
    }

17. TeamX at CheckThat!-2023: Multilingual and Multimodal Approach for Check-Worthines Detection.

    Rabindra Nath Nandi, and Firoj Alam

    In CLEF (Working Notes) , Dec 2023

    Bib

    @inproceedings{nandi2023teamx,
      author = {Nandi, Rabindra Nath and Alam, Firoj},
      booktitle = {CLEF (Working Notes)},
      pages = {394--403},
      title = {TeamX at CheckThat!-2023: Multilingual and Multimodal Approach for Check-Worthines Detection.},
      year = {2023},
    }

18. Overview of the CLEF-2023 CheckThat! Lab Task 4 on Factuality of Reporting of News Media

    Preslav Nakov, Firoj Alam, Giovanni Da San Martino , and 4 more authors

    In Working Notes of CLEF 2023 - Conference and Labs of the Evaluation Forum , Dec 2023

    Bib

    @inproceedings{clef-checkthat:2023:task4,
      author = {Nakov, Preslav and Alam, Firoj and Da San Martino, Giovanni and Hasanain, Maram and Nandi, Rabindra Nath and Azizov, Dilshod and Panayotov, Panayot},
      booktitle = {Working Notes of {CLEF} 2023 - Conference and Labs of the Evaluation Forum},
      crossref = {clef2023-workingnotes},
      date-modified = {2024-08-03 12:30:24 +0300},
      title = {Overview of the {CLEF}-2023 {CheckThat}! Lab Task 4 on Factuality of Reporting of News Media},
      year = {2023},
    }

19. 

    MEDIC: a multi-task learning dataset for disaster image classification

    Firoj Alam, Tanvirul Alam, Md Arid Hasan , and 3 more authors

    Dec 2023

    Bib

    @book{alam2023medic,
      author = {Alam, Firoj and Alam, Tanvirul and Hasan, Md Arid and Hasnat, Abul and Imran, Muhammad and Ofli, Ferda},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 12:49:01 +0300},
      journal = {Neural Computing and Applications},
      number = {3},
      pages = {2609--2632},
      publisher = {Springer},
      title = {{MEDIC}: a multi-task learning dataset for disaster image classification},
      volume = {35},
      year = {2023},
    }

20. Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis

    Md. Arid Hasan, Shudipta Das, Afiyat Anjum , and 4 more authors

    Dec 2023

    Bib

    @article{hasan2023zero,
      archiveprefix = {arXiv},
      author = {Hasan, Md. Arid and Das, Shudipta and Anjum, Afiyat and Alam, Firoj and Anjum, Anika and Sarker, Avijit and Noori, Sheak Rashed Haider},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 11:35:50 +0300},
      eprint = {2308.10783},
      primaryclass = {cs.CL},
      title = {Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis},
      year = {2023},
    }

2022

1. The CLEF-2022 CheckThat! Lab on Fighting the COVID-19 Infodemic and Fake News Detection

   Preslav Nakov, Alberto Barrón-Cedeño, Giovanni Da San Martino , and 15 more authors

   In Advances in Information Retrieval – European Conference on IR Research , Dec 2022

   Bib

   @inproceedings{CheckThat:ECIR2022,
     author = {Nakov, Preslav and Barr{\'o}n-Cede{\~{n}}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and Stru{\ss}, Julia Maria and Mandl, Thomas and M{\'\i}guez, Rub{\'e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and Li, Chengkai and Shaar, Shaden and Shahi, Gautam Kishore and Mubarak, Hamdy and Nikolov, Alex and Babulkov, Nikolay and Kartal, Yavuz Selim and Beltr{\'a}n, Javier},
     booktitle = {Advances in Information Retrieval -- European Conference on {IR} Research},
     isbn = {978-3-030-99739-7},
     noaddress = {Cham},
     noeditor = {Hagen, Matthias and Verberne, Suzan and Macdonald, Craig and Seifert, Christin and Balog, Krisztian and N{\o}rv{\aa}g, Kjetil and Setty, Vinay},
     nopublisher = {Springer International Publishing},
     pages = {416--428},
     series = {ECIR~'22},
     title = {{The CLEF-2022 CheckThat! Lab} on Fighting the {COVID-19} Infodemic and Fake News Detection},
     year = {2022},
   }

2. Overview of the WANLP 2022 Shared Task on Propaganda Detection in Arabic

   Firoj Alam, Hamdy Mubarak, Wajdi Zaghouani , and 2 more authors

   In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP) , Dec 2022

   Bib

   @inproceedings{alam-etal-2022-overview,
     address = {Abu Dhabi, United Arab Emirates (Hybrid)},
     author = {Alam, Firoj and Mubarak, Hamdy and Zaghouani, Wajdi and Da San Martino, Giovanni and Nakov, Preslav},
     booktitle = {Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)},
     date-modified = {2024-08-03 12:34:52 +0300},
     editor = {Bouamor, Houda and Al-Khalifa, Hend and Darwish, Kareem and Rambow, Owen and Bougares, Fethi and Abdelali, Ahmed and Tomeh, Nadi and Khalifa, Salam and Zaghouani, Wajdi},
     month = dec,
     pages = {108--118},
     publisher = {Association for Computational Linguistics},
     title = {Overview of the {WANLP} 2022 Shared Task on Propaganda Detection in {A}rabic},
     year = {2022},
     url = {https://aclanthology.org/2022.wanlp-1.11},
     bdsk-url-2 = {https://doi.org/10.18653/v1/2022.wanlp-1.11},
   }

3. Fact-checking, fake news, propaganda, media bias, and the covid-19 infodemic

   Preslav Nakov, Giovanni Da San Martino, and Firoj Alam

   In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining , Dec 2022

   Bib

   @inproceedings{nakov2022fact,
     author = {Nakov, Preslav and Da San Martino, Giovanni and Alam, Firoj},
     booktitle = {Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
     pages = {1632--1634},
     title = {Fact-checking, fake news, propaganda, media bias, and the covid-19 infodemic},
     year = {2022},
   }

4. Overview of the CLEF-2022 CheckThat! Lab on Fighting the COVID-19 Infodemic and Fake News Detection

   Preslav Nakov, Alberto Barrón-Cedeño, Giovanni Da San Martino , and 18 more authors

   In Proceedings of the 13th International Conference of the CLEF Association: Information Access Evaluation meets Multilinguality, Multimodality, and Visualization , Dec 2022

   Bib

   @inproceedings{clef-checkthat:2022:LNCS,
     address = {Bologna, Italy},
     author = {Nakov, Preslav and Barr\'{o}n-Cede\~{n}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and Stru\ss{}, Julia Maria and Mandl, Thomas and M\'{\i}guez, Rub\'{e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and Li, Chengkai and Shaar, Shaden and Shahi, Gautam Kishore and Mubarak, Hamdy and Nikolov, Alex and Babulkov, Nikolay and Kartal, Yavuz Selim and Beltr\'{a}n, Javier and Wiegand, Michael and Siegel, Melanie and K{\"o}hler, Juliane},
     booktitle = {Proceedings of the 13th International Conference of the {CLEF} Association: Information Access Evaluation meets Multilinguality, Multimodality, and Visualization},
     series = {CLEF~'2022},
     title = {Overview of the {CLEF}-2022 {CheckThat}! Lab on Fighting the {COVID-19} Infodemic and Fake News Detection},
     year = {2022},
   }

5. Overview of the CLEF-2022 CheckThat! Lab Task 2 on Detecting Previously Fact-Checked Claims

   Preslav Nakov, Giovanni Da San Martino, Firoj Alam , and 3 more authors

   In Working Notes of CLEF 2022—Conference and Labs of the Evaluation Forum , Dec 2022

   Bib

   @inproceedings{clef-checkthat:2022:task2,
     address = {Bologna, Italy},
     author = {Nakov, Preslav and Da San Martino, Giovanni and Alam, Firoj and Shaar, Shaden and Mubarak, Hamdy and Babulkov, Nikolay},
     booktitle = {Working Notes of {CLEF} 2022---Conference and Labs of the Evaluation Forum},
     series = {CLEF~'2022},
     title = {Overview of the {CLEF}-2022 {CheckThat}! Lab Task 2 on Detecting Previously Fact-Checked Claims},
     year = {2022},
   }

6. Z-Index at CheckThat! Lab 2022: Check-Worthiness Identification on Tweet Text

   Prerona Tarannum, Hasan Md. Arid, Firoj Alam , and 1 more author

   In Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum , Dec 2022

   Bib

   @inproceedings{clef-checkthat:2022:task1:prerona,
     address = {Bologna, Italy},
     author = {Tarannum, Prerona and Md. Arid, Hasan and Alam, Firoj and Noori, Sheak Rashed Haider},
     booktitle = {Working Notes of {CLEF} 2022 - Conference and Labs of the Evaluation Forum},
     series = {CLEF~'2022},
     title = {{Z-Index at CheckThat! Lab 2022:} Check-Worthiness Identification on Tweet Text},
     year = {2022},
   }

7. Overview of the CLEF-2022 CheckThat! Lab Task 1 on Identifying Relevant Claims in Tweets

   Preslav Nakov, Alberto Barrón-Cedeño, Giovanni Da San Martino , and 11 more authors

   In Working Notes of CLEF 2022—Conference and Labs of the Evaluation Forum , Dec 2022

   Bib

   @inproceedings{clef-checkthat:2022:task1,
     address = {Bologna, Italy},
     author = {Nakov, Preslav and Barr\'{o}n-Cede\~{n}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and M\'{\i}guez, Rub\'{e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and Li, Chengkai and Shaar, Shaden and Mubarak, Hamdy and Nikolov, Alex and Kartal, Yavuz Selim and Beltr\'{a}n, Javier},
     booktitle = {Working Notes of {CLEF} 2022---Conference and Labs of the Evaluation Forum},
     series = {CLEF~'2022},
     title = {Overview of the {CLEF}-2022 {CheckThat}! Lab Task 1 on Identifying Relevant Claims in Tweets},
     year = {2022},
   }

8. 

   ArabGend: Gender Analysis and Inference on Arabic Twitter

   Hamdy Mubarak, Shammur Absar Chowdhury, and Firoj Alam

   In Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022) , Oct 2022

   Bib

   @inproceedings{mubarak-etal-2022-arabgend,
     address = {Gyeongju, Republic of Korea},
     author = {Mubarak, Hamdy and Chowdhury, Shammur Absar and Alam, Firoj},
     booktitle = {Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)},
     date-modified = {2024-08-03 11:44:50 +0300},
     month = oct,
     pages = {124--135},
     publisher = {Association for Computational Linguistics},
     title = {{A}rab{G}end: Gender Analysis and Inference on {A}rabic {T}witter},
     year = {2022},
     url = {https://aclanthology.org/2022.wnut-1.14},
   }

9. The CLEF-2022 CheckThat! lab on fighting the COVID-19 infodemic and fake news detection

   Preslav Nakov, Alberto Barrón-Cedeño, Giovanni Da San Martino , and 8 more authors

   In European Conference on Information Retrieval , Oct 2022

   Bib

   @inproceedings{nakov2022clef,
     author = {Nakov, Preslav and Barr{\'o}n-Cede{\~n}o, Alberto and Da San Martino, Giovanni and Alam, Firoj and Stru{\ss}, Julia Maria and Mandl, Thomas and M{\'\i}guez, Rub{\'e}n and Caselli, Tommaso and Kutlu, Mucahid and Zaghouani, Wajdi and others},
     booktitle = {European Conference on Information Retrieval},
     organization = {Springer},
     pages = {416--428},
     title = {The CLEF-2022 CheckThat! lab on fighting the COVID-19 infodemic and fake news detection},
     year = {2022},
   }

10. TeamX@ DravidianLangTech-ACL2022: A Comparative Analysis for Troll-Based Meme Classification

    Rabindra Nath Nandi, Firoj Alam, and Preslav Nakov

    In Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages , Oct 2022

    Bib

    @inproceedings{nandi2022teamx,
      author = {Nandi, Rabindra Nath and Alam, Firoj and Nakov, Preslav},
      booktitle = {Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages},
      pages = {79--85},
      title = {TeamX@ DravidianLangTech-ACL2022: A Comparative Analysis for Troll-Based Meme Classification},
      year = {2022},
    }

11. Detecting the Role of an Entity in Harmful Memes: Techniques and their Limitations

    Rabindra Nath Nandi, Firoj Alam, and Preslav Nakov

    In Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations , Oct 2022
12. Half-Day Tutorial on Combating Online Hate Speech: The Role of Content, Networks, Psychology, User Behavior, etc.

    Sarah Masud, Pinkesh Pinkesh, Amitava Das , and 3 more authors

    In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining , Oct 2022

    Bib

    @inproceedings{masud2022half,
      author = {Masud, Sarah and Pinkesh, Pinkesh and Das, Amitava and Gupta, Manish and Nakov, Preslav and Chakraborty, Tanmoy},
      booktitle = {Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
      pages = {1629--1631},
      title = {Half-Day Tutorial on Combating Online Hate Speech: The Role of Content, Networks, Psychology, User Behavior, etc.},
      year = {2022},
    }

13. 

    Detecting and Understanding Harmful Memes: A Survey

    Shivam Sharma, Firoj Alam, Md. Shad Akhtar , and 7 more authors

    In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22 , Jul 2022

    Survey Track

    Bib

    @inproceedings{ijcai2022p781,
      author = {Sharma, Shivam and Alam, Firoj and Akhtar, Md. Shad and Dimitrov, Dimitar and Da San Martino, Giovanni and Firooz, Hamed and Halevy, Alon and Silvestri, Fabrizio and Nakov, Preslav and Chakraborty, Tanmoy},
      booktitle = {Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI-22}},
      date-modified = {2024-08-03 12:05:29 +0300},
      editor = {Raedt, Lud De},
      month = jul,
      note = {Survey Track},
      pages = {5597--5606},
      publisher = {International Joint Conferences on Artificial Intelligence Organization},
      title = {Detecting and Understanding Harmful Memes: A Survey},
      year = {2022},
      url = {https://doi.org/10.24963/ijcai.2022/781},
    }

14. QCRI’s COVID-19 Disinformation Detector: A System to Fight the COVID-19 Infodemic in Social Media

    Preslav Nakov, Firoj Alam, Yifan Zhang , and 2 more authors

    arXiv preprint arXiv:2204.03506, Jul 2022

    Bib

    @article{nakov2022qcri,
      author = {Nakov, Preslav and Alam, Firoj and Zhang, Yifan and Prakash, Animesh and Dalvi, Fahim},
      journal = {arXiv preprint arXiv:2204.03506},
      title = {QCRI's COVID-19 Disinformation Detector: A System to Fight the COVID-19 Infodemic in Social Media},
      year = {2022},
    }

15. ArCovidVac: Analyzing Arabic Tweets About COVID-19 Vaccination

    Hamdy Mubarak, Sabit Hassan, Shammur Absar Chowdhury , and 1 more author

    In Proceedings of the Thirteenth Language Resources and Evaluation Conference , Jun 2022

    Bib

    @inproceedings{mubarak-etal-2022-arcovidvac,
      address = {Marseille, France},
      author = {Mubarak, Hamdy and Hassan, Sabit and Chowdhury, Shammur Absar and Alam, Firoj},
      booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference},
      date-modified = {2024-08-03 11:44:50 +0300},
      editor = {Calzolari, Nicoletta and B{\'e}chet, Fr{\'e}d{\'e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Odijk, Jan and Piperidis, Stelios},
      month = jun,
      pages = {3220--3230},
      publisher = {European Language Resources Association},
      title = {{A}r{C}ovid{V}ac: Analyzing {A}rabic Tweets About {COVID}-19 Vaccination},
      year = {2022},
      url = {https://aclanthology.org/2022.lrec-1.344},
    }

16. Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document

    Shaden Shaar, Nikola Georgiev, Firoj Alam , and 3 more authors

    In Findings of the Association for Computational Linguistics: EMNLP 2022 , Dec 2022

    Abs Bib

    Given the recent proliferation of false claims online, there has been a lot of manual fact-checking effort. As this is very time-consuming, human fact-checkers can benefit from tools that can support them and make them more efficient. Here, we focus on building a system that could provide such support. Given an input document, it aims to detect all sentences that contain a claim that can be verified by some previously fact-checked claims (from a given database). The output is a re-ranked list of the document sentences, so that those that can be verified are ranked as high as possible, together with corresponding evidence. Unlike previous work, which has looked into claim retrieval, here we take a document-level perspective. We create a new manually annotated dataset for the task, and we propose suitable evaluation measures. We further experiment with a learning-to-rank approach, achieving sizable performance gains over several strong baselines. Our analysis demonstrates the importance of modeling text similarity and stance, while also taking into account the veracity of the retrieved previously fact-checked claims. We believe that this research would be of interest to fact-checkers, journalists, media, and regulatory authorities.

    @inproceedings{shaar-etal-2022-assisting,
      address = {Abu Dhabi, United Arab Emirates},
      author = {Shaar, Shaden and Georgiev, Nikola and Alam, Firoj and Da San Martino, Giovanni and Mohamed, Aisha and Nakov, Preslav},
      booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 11:35:50 +0300},
      month = dec,
      pages = {2069--2080},
      publisher = {Association for Computational Linguistics},
      title = {Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document},
      year = {2022},
      url = {https://aclanthology.org/2022.findings-emnlp.151},
      doi = {https://doi.org/10.18653/v1/2022.findings-emnlp.151},
    }

17. 

    On the Transformation of Latent Space in Fine-Tuned NLP Models

    Nadir Durrani, Hassan Sajjad, Fahim Dalvi , and 1 more author

    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , Dec 2022

    Abs Bib

    We study the evolution of latent space in fine-tuned NLP models. Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations. More specifically, we discover latent concepts in the representational space using hierarchical clustering. We then use an alignment function to gauge the similarity between the latent space of a pre-trained model and its fine-tuned version. We use traditional linguistic concepts to facilitate our understanding and also study how the model space transforms towards task-specific information. We perform a thorough analysis, comparing pre-trained and fine-tuned models across three models and three downstream tasks. The notable findings of our work are: i) the latent space of the higher layers evolve towards task-specific concepts, ii) whereas the lower layers retain generic concepts acquired in the pre-trained model, iii) we discovered that some concepts in the higher layers acquire polarity towards the output class, and iv) that these concepts can be used for generating adversarial triggers.

    @inproceedings{durrani-etal-2022-transformation,
      address = {Abu Dhabi, United Arab Emirates},
      author = {Durrani, Nadir and Sajjad, Hassan and Dalvi, Fahim and Alam, Firoj},
      booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 11:35:50 +0300},
      month = dec,
      pages = {1495--1516},
      publisher = {Association for Computational Linguistics},
      title = {On the Transformation of Latent Space in Fine-Tuned {NLP} Models},
      year = {2022},
      url = {https://aclanthology.org/2022.emnlp-main.97},
      doi = {https://doi.org/10.18653/v1/2022.emnlp-main.97},
    }

18. 

    A Survey on Multimodal Disinformation Detection

    Firoj Alam, Stefano Cresci, Tanmoy Chakraborty , and 6 more authors

    In Proceedings of the 29th International Conference on Computational Linguistics , Oct 2022

    Abs Bib

    Recent years have witnessed the proliferation of offensive content online such as fake news, propaganda, misinformation, and disinformation. While initially this was mostly about textual content, over time images and videos gained popularity, as they are much easier to consume, attract more attention, and spread further than text. As a result, researchers started leveraging different modalities and combinations thereof to tackle online multimodal offensive content. In this study, we offer a survey on the state-of-the-art on multimodal disinformation detection covering various combinations of modalities: text, images, speech, video, social media network structure, and temporal information. Moreover, while some studies focused on factuality, others investigated how harmful the content is. While these two components in the definition of disinformation – (i) factuality, and (ii) harmfulness –, are equally important, they are typically studied in isolation. Thus, we argue for the need to tackle disinformation detection by taking into account multiple modalities as well as both factuality and harmfulness, in the same framework. Finally, we discuss current challenges and future research directions.

    @inproceedings{alam-etal-2022-survey,
      address = {Gyeongju, Republic of Korea},
      author = {Alam, Firoj and Cresci, Stefano and Chakraborty, Tanmoy and Silvestri, Fabrizio and Dimitrov, Dimiter and Martino, Giovanni Da San and Shaar, Shaden and Firooz, Hamed and Nakov, Preslav},
      booktitle = {Proceedings of the 29th International Conference on Computational Linguistics},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 11:35:50 +0300},
      month = oct,
      pages = {6625--6643},
      publisher = {International Committee on Computational Linguistics},
      title = {A Survey on Multimodal Disinformation Detection},
      year = {2022},
      url = {https://aclanthology.org/2022.coling-1.576},
    }

19. 

    Analyzing Encoded Concepts in Transformer Language Models

    Hassan Sajjad, Nadir Durrani, Fahim Dalvi , and 3 more authors

    In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies , Jul 2022

    Abs Bib

    We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained lan-guage models. It uses clustering to discover the encoded concepts and explains them by aligning with a large set of human-defined concepts. Our analysis on seven transformer language models reveal interesting insights: i) the latent space within the learned representations overlap with different linguistic concepts to a varying degree, ii) the lower layers in the model are dominated by lexical concepts (e.g., affixation) and linguistic ontologies (e.g. Word-Net), whereas the core-linguistic concepts (e.g., morphology, syntactic relations) are better represented in the middle and higher layers, iii) some encoded concepts are multi-faceted and cannot be adequately explained using the existing human-defined concepts.

    @inproceedings{sajjad-etal-2022-analyzing,
      address = {Seattle, United States},
      author = {Sajjad, Hassan and Durrani, Nadir and Dalvi, Fahim and Alam, Firoj and Khan, Abdul and Xu, Jia},
      booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 11:35:50 +0300},
      month = jul,
      pages = {3082--3101},
      publisher = {Association for Computational Linguistics},
      title = {Analyzing Encoded Concepts in Transformer Language Models},
      year = {2022},
      url = {https://aclanthology.org/2022.naacl-main.225},
      doi = {https://doi.org/10.18653/v1/2022.naacl-main.225},
    }

20. The Role of Context in Detecting Previously Fact-Checked Claims

    Shaden Shaar, Firoj Alam, Giovanni Da San Martino , and 1 more author

    In Findings of the Association for Computational Linguistics: NAACL 2022 , Jul 2022

    Abs Bib

    Recent years have seen the proliferation of disinformation and fake news online. Traditional approaches to mitigate these issues is to use manual or automatic fact-checking. Recently, another approach has emerged: checking whether the input claim has previously been fact-checked, which can be done automatically, and thus fast, while also offering credibility and explainability, thanks to the human fact-checking and explanations in the associated fact-checking article. Here, we focus on claims made in a political debate and we study the impact of modeling the context of the claim: both on the source side, i.e., in the debate, as well as on the target side, i.e., in the fact-checking explanation document. We do this by modeling the local context, the global context, as well as by means of co-reference resolution, and multi-hop reasoning over the sentences of the document describing the fact-checked claim. The experimental results show that each of these represents a valuable information source, but that modeling the source-side context is most important, and can yield 10+ points of absolute improvement over a state-of-the-art model.

    @inproceedings{shaar-etal-2022-role,
      address = {Seattle, United States},
      author = {Shaar, Shaden and Alam, Firoj and Da San Martino, Giovanni and Nakov, Preslav},
      booktitle = {Findings of the Association for Computational Linguistics: NAACL 2022},
      date-added = {2024-08-03 11:35:50 +0300},
      date-modified = {2024-08-03 11:35:50 +0300},
      month = jul,
      pages = {1619--1631},
      publisher = {Association for Computational Linguistics},
      title = {The Role of Context in Detecting Previously Fact-Checked Claims},
      year = {2022},
      url = {https://aclanthology.org/2022.findings-naacl.122},
      doi = {https://doi.org/10.18653/v1/2022.findings-naacl.122},
    }

21. 

    Discovering Latent Concepts Learned in BERT

    Fahim Dalvi, Abdul Rafae Khan, Firoj Alam , and 3 more authors

    In International Conference on Learning Representations , Jul 2022

    Bib

    @inproceedings{dalvi2022discovering,
      author = {Dalvi, Fahim and Khan, Abdul Rafae and Alam, Firoj and Durrani, Nadir and Xu, Jia and Sajjad, Hassan},
      booktitle = {International Conference on Learning Representations},
      title = {Discovering Latent Concepts Learned in {BERT}},
      year = {2022},
      url = {https://openreview.net/forum?id=POTMtpYI1xH},
    }

22. Role of Social Media Imagery in Disaster Informatics

    Firoj Alam, Kashif Ahmad, Md. Arid Hasan , and 2 more authors

    Jul 2022

    Abs Bib

    The recent literature reports several practical and important use cases of social media informatics where artificial intelligence (AI), machine learning (ML), and other relevant technologies are employed to analyze human sufferings and infrastructure damage in natural disasters. While the textual content of social media platforms conveys relevant and useful information during a disaster, social media imagery content has also been proven very effective in analyzing the scale of damage to infrastructures such as roads, bridges, and buildings. Moreover, disaster-related visual content could also be analyzed to extract people’s perceptions, emotions, sentiments, and responses to disasters, which can help different stakeholders, such as humanitarian organizations and policy-makers. Assessing such aspects of disaster events requires effective and efficient image processing methods to process a large amount social media content. This chapter reviews state-of-the-art techniques and shows their utility in processing social media image streams during disaster response for a diversified set of applications. It also highlights the key applications, challenges, available shared resources (datasets and models), tasks, and future research directions. This chapter will provide a ground for future research and a good starting point for the researchers in the domain.

    @inbook{Alam2022,
      address = {Singapore},
      author = {Alam, Firoj and Ahmad, Kashif and Hasan, Md. Arid and Ofli, Ferda and Imran, Muhammad},
      booktitle = {International Handbook of Disaster Research},
      date-modified = {2024-08-03 07:58:24 +0300},
      editor = {Singh, Amita},
      isbn = {978-981-16-8800-3},
      pages = {1--21},
      publisher = {Springer Nature Singapore},
      title = {Role of Social Media Imagery in Disaster Informatics},
      year = {2022},
      url = {https://doi.org/10.1007/978-981-16-8800-3_170-1},
    }

23. Robust Training of Social Media Image Classification Models

    Firoj Alam, Tanvirul Alam, Ferda Ofli , and 1 more author

    IEEE Transactions on Computational Social Systems, Jul 2022

    https://ieeexplore.ieee.org/document/9999229

    Bib

    @article{alam2022robust,
      author = {Alam, Firoj and Alam, Tanvirul and Ofli, Ferda and Imran, Muhammad},
      date-modified = {2024-08-03 07:58:24 +0300},
      journal = {IEEE Transactions on Computational Social Systems},
      note = {https://ieeexplore.ieee.org/document/9999229},
      pages = {1-20},
      title = {Robust Training of Social Media Image Classification Models},
      year = {2022},
      url = {https://doi.org/10.1109/TCSS.2022.3230839},
    }

24. MEDIC: a multi-task learning dataset for disaster image classification

    Firoj Alam, Tanvirul Alam, Md Arid Hasan , and 3 more authors

    Neural Computing and Applications, Jul 2022

    https://link.springer.com/article/10.1007/s00521-022-07717-0

    Bib Code

    @article{alam2022medic,
      author = {Alam, Firoj and Alam, Tanvirul and Hasan, Md Arid and Hasnat, Abul and Imran, Muhammad and Ofli, Ferda},
      data = {https://doi.org/10.5281/zenodo.6625120},
      journal = {Neural Computing and Applications},
      note = {https://link.springer.com/article/10.1007/s00521-022-07717-0},
      pages = {1--24},
      publisher = {Springer},
      title = {{MEDIC:} a multi-task learning dataset for disaster image classification},
      year = {2022},
    }

25. Adversarial NLP for Social Network Applications: Attacks, Defenses, and Research Directions

    Izzat Alsmadi, Kashif Ahmad, Mahmoud Nazzal , and 4 more authors

    IEEE Transactions on Computational Social Systems, Jul 2022

    Bib

    @article{Alsmadi2022,
      author = {Alsmadi, Izzat and Ahmad, Kashif and Nazzal, Mahmoud and Alam, Firoj and Al-Fuqaha, Ala and Khreishah, Abdallah and Algosaibi, Abdulelah},
      date-modified = {2024-08-03 07:58:24 +0300},
      journal = {IEEE Transactions on Computational Social Systems},
      pages = {1-20},
      title = {Adversarial NLP for Social Network Applications: Attacks, Defenses, and Research Directions},
      year = {2022},
      url = {https://doi.org/10.1109/TCSS.2022.3218743},
    }

26. Global user-level perception of COVID-19 contact tracing applications: Data-driven approach using natural language processing

    Kashif Ahmad, Firoj Alam, Junaid Qadir , and 8 more authors

    JMIR Formative Research, Jul 2022

    https://pubmed.ncbi.nlm.nih.gov/35389357/

    Bib

    @article{ahmad2022global,
      author = {Ahmad, Kashif and Alam, Firoj and Qadir, Junaid and Qolomany, Basheer and Khan, Imran and Khan, Talhat and Suleman, Muhammad and Said, Naina and Hassan, Syed Zohaib and Gul, Asma and others},
      journal = {JMIR Formative Research},
      note = {https://pubmed.ncbi.nlm.nih.gov/35389357/},
      number = {5},
      pages = {e36238},
      publisher = {JMIR Publications Toronto, Canada},
      title = {Global user-level perception of COVID-19 contact tracing applications: Data-driven approach using natural language processing},
      volume = {6},
      year = {2022},
    }

2021

1. The CLEF-2021 CheckThat! lab on detecting check-worthy claims, previously fact-checked claims, and fake news

   Preslav Nakov, Giovanni Da San Martino, Tamer Elsayed , and 8 more authors

   In European Conference on Information Retrieval , Jul 2021

   Bib

   @inproceedings{nakov2021clef,
     author = {Nakov, Preslav and Da San Martino, Giovanni and Elsayed, Tamer and Barr{\'o}n-Cedeno, Alberto and M{\'\i}guez, Rub{\'e}n and Shaar, Shaden and Alam, Firoj and Haouari, Fatima and Hasanain, Maram and Babulkov, Nikolay and others},
     booktitle = {European Conference on Information Retrieval},
     organization = {Springer},
     pages = {639--649},
     title = {The CLEF-2021 CheckThat! lab on detecting check-worthy claims, previously fact-checked claims, and fake news},
     year = {2021},
   }

2. SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images

   Dimitar Dimitrov, Bishr Bin Ali, Shaden Shaar , and 5 more authors

   In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021) , Jul 2021

   Bib

   @inproceedings{dimitrov2021semeval,
     author = {Dimitrov, Dimitar and Ali, Bishr Bin and Shaar, Shaden and Alam, Firoj and Silvestri, Fabrizio and Firooz, Hamed and Nakov, Preslav and Da San Martino, Giovanni},
     booktitle = {Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)},
     pages = {70--98},
     title = {SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images},
     year = {2021},
   }

3. Overview of the CLEF-2021 CheckThat! Lab Task 1 on Check-Worthiness Estimation in Tweets and Political Debates

   Shaden Shaar, Maram Hasanain, Bayan Hamdan , and 12 more authors

   Working Notes of CLEF, Jul 2021

   Bib

   @article{shaar2021alberto,
     author = {Shaar, Shaden and Hasanain, Maram and Hamdan, Bayan and Ali, Zien Sheikh and Haouari, Fatima and Nikolov, Alex and Kutlu, Mucahid and Kartal, Yavuz Selim and Alam, Firoj and Da San Martino, Giovanni and n-Cede no, Alberto Barr{\'o} and M{\'\i}guez, Rub{\'e}n and Beltr{\'a}n, Javier and Elsayed, Tamer and Nakov, Preslav},
     date-modified = {2022-06-16 13:33:39 +0000},
     journal = {Working Notes of CLEF},
     title = {Overview of the CLEF-2021 CheckThat! Lab Task 1 on Check-Worthiness Estimation in Tweets and Political Debates},
     year = {2021},
   }

4. Automated Fact-Checking for Assisting Human Fact-Checkers

   Preslav Nakov, David Corney, Maram Hasanain , and 6 more authors

   In Proceedings of the 30th International Joint Conference on Artificial Intelligence , Jul 2021

   Bib

   @inproceedings{survey:2021:ai:fact-checkers,
     author = {Nakov, Preslav and Corney, David and Hasanain, Maram and Alam, Firoj and Elsayed, Tamer and Barr{\'{o}}n{-}Cede{\~{n}}o, Alberto and Papotti, Paolo and Shaar, Shaden and {Da San Martino}, Giovanni},
     booktitle = {Proceedings of the 30th International Joint Conference on Artificial Intelligence},
     pages = {4551--4558},
     series = {IJCAI~'21},
     title = {Automated Fact-Checking for Assisting Human Fact-Checkers},
     year = {2021},
   }

5. A Second Pandemic? Analysis of Fake News about COVID-19 Vaccines in Qatar

   Preslav Nakov, Firoj Alam, Shaden Shaar , and 2 more authors

   In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021) , Sep 2021

   Abs Bib

   While COVID-19 vaccines are finally becoming widely available, a second pandemic that revolves around the circulation of anti-vaxxer “fake news” may hinder efforts to recover from the first one. With this in mind, we performed an extensive analysis of Arabic and English tweets about COVID-19 vaccines, with focus on messages originating from Qatar. We found that Arabic tweets contain a lot of false information and rumors, while English tweets are mostly factual. However, English tweets are much more propagandistic than Arabic ones. In terms of propaganda techniques, about half of the Arabic tweets express doubt, and 1/5 use loaded language, while English tweets are abundant in loaded language, exaggeration, fear, name-calling, doubt, and flag-waving. Finally, in terms of framing, Arabic tweets adopt a health and safety perspective, while in English economic concerns dominate.

   @inproceedings{nakov-etal-2021-second,
     address = {Held Online},
     author = {Nakov, Preslav and Alam, Firoj and Shaar, Shaden and Da San Martino, Giovanni and Zhang, Yifan},
     booktitle = {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)},
     date-modified = {2024-08-03 12:41:40 +0300},
     editor = {Mitkov, Ruslan and Angelova, Galia},
     month = sep,
     pages = {1010--1021},
     publisher = {INCOMA Ltd.},
     title = {A Second Pandemic? Analysis of Fake News about {COVID}-19 Vaccines in {Q}atar},
     year = {2021},
     url = {https://aclanthology.org/2021.ranlp-1.114},
   }

6. A survey on computational propaganda detection

   Giovanni Da San Martino, Stefano Cresci, Alberto Barrón-Cedeño , and 3 more authors

   In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence , Sep 2021

   Bib

   @inproceedings{da2021survey,
     author = {Da San Martino, Giovanni and Cresci, Stefano and Barr{\'o}n-Cede{\~n}o, Alberto and Yu, Seunghak and Di Pietro, Roberto and Nakov, Preslav},
     booktitle = {Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence},
     pages = {4826--4832},
     title = {A survey on computational propaganda detection},
     year = {2021},
   }

7. COVID-19 in Bulgarian Social Media: Factuality, Harmfulness, Propaganda, and Framing

   Preslav Nakov, Firoj Alam, Shaden Shaar , and 2 more authors

   In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021) , Sep 2021

   Abs Bib

   With the emergence of the COVID-19 pandemic, the political and the medical aspects of disinformation merged as the problem got elevated to a whole new level to become the first global infodemic. Fighting this infodemic is currently ranked very high on the list of priorities of the World Health Organization, with dangers ranging from promoting fake cures, rumors, and conspiracy theories to spreading xenophobia and panic. With this in mind, we studied how COVID-19 is discussed in Bulgarian social media in terms of factuality, harmfulness, propaganda, and framing. We found that most Bulgarian tweets contain verifiable factual claims, are factually true, are of potential public interest, are not harmful, and are too trivial to fact-check; moreover, zooming into harmful tweets, we found that they spread not only rumors but also panic. We further analyzed articles shared in Bulgarian partisan pro/con-COVID-19 Facebook groups and found that propaganda is more prevalent in skeptical articles, which use doubt, flag waving, and slogans to convey their message; in contrast, concerned ones appeal to emotions, fear, and authority; moreover, skeptical articles frame the issue as one of quality of life, policy, legality, economy, and politics, while concerned articles focus on health & safety. We release our manually and automatically analyzed datasets to enable further research.

   @inproceedings{nakov-etal-2021-covid,
     address = {Held Online},
     author = {Nakov, Preslav and Alam, Firoj and Shaar, Shaden and Da San Martino, Giovanni and Zhang, Yifan},
     booktitle = {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)},
     date-modified = {2024-08-03 12:42:37 +0300},
     editor = {Mitkov, Ruslan and Angelova, Galia},
     month = sep,
     pages = {997--1009},
     publisher = {INCOMA Ltd.},
     title = {{COVID}-19 in {B}ulgarian Social Media: Factuality, Harmfulness, Propaganda, and Framing},
     year = {2021},
     url = {https://aclanthology.org/2021.ranlp-1.113},
   }

8. Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda

   Anna Feldman, Giovanni Da San Martino, Chris Leberknight , and 1 more author

   In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda , Sep 2021

   Bib

   @inproceedings{feldman2021proceedings,
     author = {Feldman, Anna and Da San Martino, Giovanni and Leberknight, Chris and Nakov, Preslav},
     booktitle = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
     title = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
     year = {2021},
   }

9. Social Media Images Classification Models for Real-time Disaster Response

   Firoj Alam, Tanvirul Alam, Ferda Ofli , and 1 more author

   arXiv:2104.04184, Sep 2021

   Bib

   @article{alam2021social,
     archiveprefix = {arXiv},
     author = {Alam, Firoj and Alam, Tanvirul and Ofli, Ferda and Imran, Muhammad},
     journal = {arXiv:2104.04184},
     primaryclass = {cs.CV},
     title = {Social Media Images Classification Models for Real-time Disaster Response},
     year = {2021},
   }

10. Findings of the NLP4IF-2021 Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detection

    Shaden Shaar, Firoj Alam, Giovanni Da San Martino , and 4 more authors

    In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda , Sep 2021

    Bib

    @inproceedings{shaar2021findings,
      author = {Shaar, Shaden and Alam, Firoj and Da San Martino, Giovanni and Nikolov, Alex and Zaghouani, Wajdi and Nakov, Preslav and Feldman, Anna},
      booktitle = {Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda},
      pages = {82--92},
      title = {Findings of the NLP4IF-2021 Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detection},
      year = {2021},
    }

11. HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks

    Firoj Alam, Umair Qazi, Muhammad Imran , and 1 more author

    In ICWSM , Sep 2021

    https://ojs.aaai.org/index.php/ICWSM/article/view/18116

    Bib Code

    @inproceedings{alam2021humaid,
      author = {Alam, Firoj and Qazi, Umair and Imran, Muhammad and Ofli, Ferda},
      booktitle = {ICWSM},
      data = {https://doi.org/10.7910/DVN/A7NVF7},
      note = {https://ojs.aaai.org/index.php/ICWSM/article/view/18116},
      title = {{HumAID}: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks},
      year = {2021},
    }

12. CrisisBench: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing

    Firoj Alam, Hassan Sajjad, Muhammad Imran , and 1 more author

    In Proceedings of the International AAAI Conference on Web and Social Media , Sep 2021

    https://ojs.aaai.org/index.php/ICWSM/article/view/18115

    Bib Code

    @inproceedings{alam2020standardizing,
      author = {Alam, Firoj and Sajjad, Hassan and Imran, Muhammad and Ofli, Ferda},
      booktitle = {Proceedings of the International AAAI Conference on Web and Social Media},
      data = {https://crisisnlp.qcri.org/crisis_datasets_benchmarks},
      note = {https://ojs.aaai.org/index.php/ICWSM/article/view/18115},
      title = {{CrisisBench}: Benchmarking Crisis-related Social Media Datasets for Humanitarian Information Processing},
      year = {2021},
    }

13. A review of bangla natural language processing tasks and the utility of transformer models

    Firoj Alam, Arid Hasan, Tanvirul Alam , and 4 more authors

    arXiv preprint arXiv:2107.03844, Sep 2021

    https://arxiv.org/abs/2107.03844

    Bib Code

    @article{alam2021review,
      author = {Alam, Firoj and Hasan, Arid and Alam, Tanvirul and Khan, Akib and Tajrin, Janntatul and Khan, Naira and Chowdhury, Shammur Absar},
      data = {https://github.com/banglanlp/bnlp-resources},
      journal = {arXiv preprint arXiv:2107.03844},
      note = {https://arxiv.org/abs/2107.03844},
      title = {A review of bangla natural language processing tasks and the utility of transformer models},
      year = {2021},
    }

2020

1. Descriptive and visual summaries of disaster events using artificial intelligence techniques: case studies of Hurricanes Harvey, Irma, and Maria

   Firoj Alam, Ferda Ofli, and Muhammad Imran

   Behaviour & Information Technology, Sep 2020

   https://www.tandfonline.com/doi/full/10.1080/0144929X.2019.1610908

   Abs Bib

   People increasingly use microblogging platforms such as Twitter during natural disasters and emergencies. Research studies have revealed the usefulness of the data available on Twitter for several disaster response tasks. However, making sense of social media data is a challenging task due to several reasons such as limitations of available tools to analyse high-volume and high-velocity data streams, dealing with information overload, among others. To eliminate such limitations, in this work, we first show that textual and imagery content on social media provide complementary information useful to improve situational awareness. We then explore ways in which various Artificial Intelligence techniques from Natural Language Processing and Computer Vision fields can exploit such complementary information generated during disaster events. Finally, we propose a methodological approach that combines several computational techniques effectively in a unified framework to help humanitarian organisations in their relief efforts. We conduct extensive experiments using textual and imagery content from millions of tweets posted during the three major disaster events in the 2017 Atlantic Hurricane season. Our study reveals that the distributions of various types of useful information can inform crisis managers and responders and facilitate the development of future automated systems for disaster management.

   @article{alam2020descriptive,
     author = {Alam, Firoj and Ofli, Ferda and Imran, Muhammad},
     journal = {Behaviour \& Information Technology},
     note = {https://www.tandfonline.com/doi/full/10.1080/0144929X.2019.1610908},
     number = {3},
     pages = {288--318},
     publisher = {Taylor \& Francis},
     title = {Descriptive and visual summaries of disaster events using artificial intelligence techniques: case studies of Hurricanes Harvey, Irma, and Maria},
     volume = {39},
     year = {2020},
   }

2. Rapid damage assessment using social media images by combining human and machine intelligence

   Muhammad Imran, Firoj Alam, Umair Qazi , and 2 more authors

   In 17th International Conference on Information Systems for Crisis Response and Management , Sep 2020

   Bib

   @inproceedings{imran2020rapid,
     author = {Imran, Muhammad and Alam, Firoj and Qazi, Umair and Peterson, Steve and Ofli, Ferda},
     booktitle = {17th International Conference on Information Systems for Crisis Response and Management},
     pages = {761--773},
     title = {Rapid damage assessment using social media images by combining human and machine intelligence},
     year = {2020},
   }

3. Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response

   Ferda Ofli, Firoj Alam, and Muhammad Imran

   In Proceedings of the Information Systems for Crisis Response and Management , May 2020

   Bib

   @inproceedings{multimodalbaseline2020,
     author = {Ofli, Ferda and Alam, Firoj and Imran, Muhammad},
     booktitle = {Proceedings of the Information Systems for Crisis Response and Management},
     keywords = {Multimodal deep learning, Multimedia content, Natural disasters, Crisis Computing, Social media},
     month = may,
     title = {Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response},
     year = {2020},
   }

4. Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response

   Firoj Alam, Ferda Ofli, Muhammad Imran , and 2 more authors

   In IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) , May 2020

   Bib

   @inproceedings{FAlam:ASONAM20,
     author = {Alam, Firoj and Ofli, Ferda and Imran, Muhammad and Alam, Tanvirul and Qazi, Umair},
     booktitle = {IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)},
     date-modified = {2024-08-03 07:58:24 +0300},
     pages = {151-158},
     title = {Deep Learning Benchmarks and Datasets for Social Media Image Classification for Disaster Response},
     year = {2020},
     url = {https://doi.org/10.1109/ASONAM49781.2020.9381294},
   }

5. Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview

   Ferda Ofli, Muhammad Imran, and Firoj Alam

   May 2020

   https://link.springer.com/chapter/10.1007/978-981-15-4291-6_5

   Abs Bib

   The ever-increasing popularity of social media platforms has transformed the way in which information is shared during disasters and mass emergencies. Information that emanates from social media, especially in the early hours of a disaster when little-to-no information is available from other traditional sources, can be extremely valuable for emergency responders and decision makers to gain situational awareness and plan relief efforts. To capitalize on this potential, extensive research and development activities have been conducted over the last decade to build technologies to support various humanitarian aid tasks. In this paper, we provide an overview of the literature on using artificial intelligence and social media for disaster response and management from three perspectives: datasets, research studies, and systems. Then, we present further discussion on open research problems and future directions in the crisis informatics domain.

   @inbook{ofli2020using,
     author = {Ofli, Ferda and Imran, Muhammad and Alam, Firoj},
     booktitle = {AI and Robotics in Disaster Studies},
     note = {https://link.springer.com/chapter/10.1007/978-981-15-4291-6_5},
     pages = {63--81},
     publisher = {Springer},
     title = {Using Artificial Intelligence and Social Media for Disaster Response and Management: An Overview},
     year = {2020},
   }

2019

1. CrisisDPS: Crisis Data Processing Services

   Firoj Alam, Imran Muhammad, and Ofli Ferda

   In Proceedings of the International Conference on Information Systems for Crisis Response and Management (ISCRAM) , May 2019

   Bib

   @inproceedings{Alam2019,
     author = {Alam, Firoj and Muhammad, Imran and Ferda, Ofli},
     booktitle = {Proceedings of the International Conference on Information Systems for Crisis Response and Management (ISCRAM)},
     title = {CrisisDPS: Crisis Data Processing Services},
     year = {2019},
   }

2. Automatic Labeling Affective Scenes in Spoken Conversations

   Firoj Alam, Morena Danieli, and Giuseppe Riccardi

   May 2019

   https://link.springer.com/chapter/10.1007/978-3-319-95996-2_6

   Abs Bib

   Research in affective computing has mainly focused on analyzing human emotional states as perceivable within limited contexts such as speech utterances. In our study, we focus on the dynamic transitions of the emotional states that are appearing throughout the conversations and investigate computational models to automatically label emotional states using the proposed affective scene framework. An affective scene includes a complete sequence of emotional states in a conversation from its start to its end. Affective scene instances include different patterns of behavior such as who manifests an emotional state, when it is manifested, and which kinds of changes occur due to the influence of one’s emotion onto another interlocutor. In this paper, we present the design and training of an automatic affective scene segmentation and classification system for spoken conversations. We comparatively evaluate the contributions of different feature types in the acoustic, lexical and psycholinguistic space and their correlations and combination.

   @inbook{alam2019automatic,
     author = {Alam, Firoj and Danieli, Morena and Riccardi, Giuseppe},
     booktitle = {Cognitive Infocommunications, Theory and Applications},
     note = {https://link.springer.com/chapter/10.1007/978-3-319-95996-2_6},
     pages = {109--130},
     publisher = {Springer},
     title = {Automatic Labeling Affective Scenes in Spoken Conversations},
     year = {2019},
   }

2018

1. Domain Adaptation with Adversarial Training and Graph Embeddings

   Firoj Alam, Shafiq Joty, and Muhammad Imran

   In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , Jul 2018

   Abs Bib

   The success of deep neural networks (DNNs) is heavily dependent on the availability of labeled data. However, obtaining labeled data is a big challenge in many real-world problems. In such scenarios, a DNN model can leverage labeled and unlabeled data from a related domain, but it has to deal with the shift in data distributions between the source and the target domains. In this paper, we study the problem of classifying social media posts during a crisis event (e.g., Earthquake). For that, we use labeled and unlabeled data from past similar events (e.g., Flood) and unlabeled data for the current event. We propose a novel model that performs adversarial learning based domain adaptation to deal with distribution drifts and graph based semi-supervised learning to leverage unlabeled data within a single unified deep learning framework. Our experiments with two real-world crisis datasets collected from Twitter demonstrate significant improvements over several baselines.

   @inproceedings{alam-etal-2018-domain,
     address = {Melbourne, Australia},
     author = {Alam, Firoj and Joty, Shafiq and Imran, Muhammad},
     booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     date-added = {2024-08-03 11:33:48 +0300},
     date-modified = {2024-08-03 11:33:48 +0300},
     month = jul,
     pages = {1077--1087},
     publisher = {Association for Computational Linguistics},
     title = {Domain Adaptation with Adversarial Training and Graph Embeddings},
     year = {2018},
     url = {https://aclanthology.org/P18-1099},
     doi = {https://doi.org/10.18653/v1/P18-1099},
   }

2. Annotating and modeling empathy in spoken conversations

   Firoj Alam, Morena Danieli, and Giuseppe Riccardi

   Computer Speech & Language, Jul 2018

   https://www.sciencedirect.com/science/article/abs/pii/S088523081730133X

   Abs Bib

   Empathy, as defined in behavioral sciences, expresses the ability of human beings to recognize, understand and react to emotions, attitudes and beliefs of others. In this paper, we address two related problems in automatic affective behavior analysis: the design of the annotation protocol and the automatic recognition of empathy from human–human dyadic spoken conversations. We propose and evaluate an annotation scheme for empathy inspired by the modal model of emotions. The annotation scheme was evaluated on a corpus of real-life, dyadic spoken conversations. In the context of behavioral analysis, we designed an automatic segmentation and classification system for empathy. Given the different speech and language levels of representation where empathy may be communicated, we investigated features derived from the lexical and acoustic spaces. The feature development process was designed to support both the fusion and automatic selection of relevant features from a high dimensional space. The automatic classification system was evaluated on call center conversations where it showed significantly better performance than the baseline.

   @article{alam2018annotating,
     author = {Alam, Firoj and Danieli, Morena and Riccardi, Giuseppe},
     journal = {Computer Speech \& Language},
     note = {https://www.sciencedirect.com/science/article/abs/pii/S088523081730133X},
     pages = {40--61},
     publisher = {Elsevier},
     title = {Annotating and modeling empathy in spoken conversations},
     volume = {50},
     year = {2018},
   }

3. Processing social media images by combining human and machine computing during crises

   Firoj Alam, Ferda Ofli, and Muhammad Imran

   International Journal of Human–Computer Interaction, Jul 2018

   https://www.tandfonline.com/doi/abs/10.1080/10447318.2018.1427831

   Abs Bib

   The extensive use of social media platforms, especially during disasters, creates unique opportunities for humanitarian organizations to gain situational awareness as disaster unfolds. In addition to textual content, people post overwhelming amounts of imagery content on social networks within minutes of a disaster hit. Studies point to the importance of this online imagery content for emergency response. Despite recent advances in computer vision research, making sense of the imagery content in real-time during disasters remains a challenging task. One of the important challenges is that a large proportion of images shared on social media is redundant or irrelevant, which requires robust filtering mechanisms. Another important challenge is that images acquired after major disasters do not share the same characteristics as those in large-scale image collections with clean annotations of well-defined object categories such as house, car, airplane, cat, dog, etc., used traditionally in computer vision research. To tackle these challenges, we present a social media image processing pipeline that combines human and machine intelligence to perform two important tasks: (i) capturing and filtering of social media imagery content (i.e., real-time image streaming, de-duplication, and relevancy filtering); and (ii) actionable information extraction (i.e., damage severity assessment) as a core situational awareness task during an on-going crisis event. Results obtained from extensive experiments on real-world crisis datasets demonstrate the significance of the proposed pipeline for optimal utilization of both human and machine computing resources.

   @article{alam2018processing,
     author = {Alam, Firoj and Ofli, Ferda and Imran, Muhammad},
     journal = {International Journal of Human--Computer Interaction},
     note = {https://www.tandfonline.com/doi/abs/10.1080/10447318.2018.1427831},
     number = {4},
     pages = {311--327},
     publisher = {Taylor \& Francis},
     title = {Processing social media images by combining human and machine computing during crises},
     volume = {34},
     year = {2018},
   }

4. Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets

   Firoj Alam, Shafiq Joty, and Muhammad Imran

   In Proceedings of the International AAAI Conference on Web and Social Media , Jul 2018

   Bib

   @inproceedings{alam2018graph,
     author = {Alam, Firoj and Joty, Shafiq and Imran, Muhammad},
     booktitle = {Proceedings of the International AAAI Conference on Web and Social Media},
     number = {1},
     title = {Graph based semi-supervised learning with convolution neural networks to classify crisis related tweets},
     volume = {12},
     year = {2018},
   }

5. CrisisMMD: Multimodal twitter datasets from natural disasters

   Firoj Alam, Ferda Ofli, and Muhammad Imran

   In Proceedings of the International AAAI Conference on Web and Social Media , Jun 2018

   Bib

   @inproceedings{alam2018crisismmd,
     author = {Alam, Firoj and Ofli, Ferda and Imran, Muhammad},
     booktitle = {Proceedings of the International AAAI Conference on Web and Social Media},
     language = {English},
     month = jun,
     pages = {465--473},
     title = {{CrisisMMD:} Multimodal twitter datasets from natural disasters},
     year = {2018},
   }

2017

1. Image4Act: Online Social Media Image Processing for Disaster Response.

   Firoj Alam, Muhammad Imran, and Ferda Ofli

   In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining , Jun 2017

   Bib

   @inproceedings{alam17demo,
     author = {Alam, Firoj and Imran, Muhammad and Ofli, Ferda},
     booktitle = {Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
     pages = {1--4},
     title = {{Image4Act}: Online Social Media Image Processing for Disaster Response.},
     year = {2017},
   }

2. Automatic Image Filtering on Social Networks Using Deep Learning and Perceptual Hashing During Crises

   Dat Tien Nguyen, Firoj Alam, Ferda Ofli , and 1 more author

   In Proc. of ISCRAM , May 2017

   Bib

   @inproceedings{nguyen2017automatic,
     author = {Nguyen, Dat Tien and Alam, Firoj and Ofli, Ferda and Imran, Muhammad},
     booktitle = {Proc. of {ISCRAM}},
     month = may,
     title = {Automatic Image Filtering on Social Networks Using Deep Learning and Perceptual Hashing During Crises},
     year = {2017},
   }

2016

1. A Knowledge-Poor Approach to Chemical-Disease Relation Extraction

   Firoj Alam, Anna Corazza, Alberto Lavelli , and 1 more author

   The Journal of Biological Databases and Curation, May 2016

   https://academic.oup.com/database/article/doi/10.1093/database/baw071/2630422

   Abs Bib

   The article describes a knowledge-poor approach to the task of extracting Chemical-Disease Relations from PubMed abstracts. A first version of the approach was applied during the participation in the BioCreative V track 3, both in Disease Named Entity Recognition and Normalization (DNER) and in Chemical-induced diseases (CID) relation extraction. For both tasks, we have adopted a general-purpose approach based on machine learning techniques integrated with a limited number of domain-specific knowledge resources and using freely available tools for preprocessing data. Crucially, the system only uses the data sets provided by the organizers. The aim is to design an easily portable approach with a limited need of domain-specific knowledge resources. In the participation in the BioCreative V task, we ranked 5 out of 16 in DNER, and 7 out of 18 in CID. In this article, we present our follow-up study in particular on CID by performing further experiments, extending our approach and improving the performance.

   @article{alamRE2016,
     author = {Alam, Firoj and Corazza, Anna and Lavelli, Alberto and Zanoli, Roberto},
     journal = {The Journal of Biological Databases and Curation},
     note = {https://academic.oup.com/database/article/doi/10.1093/database/baw071/2630422},
     title = {A Knowledge-Poor Approach to Chemical-Disease Relation Extraction},
     year = {2016},
   }

2. In the mood for sharing contents: Emotions, personality and interaction styles in the diffusion of news

   Fabio Celli, Arindam Ghosh, Firoj Alam , and 1 more author

   Information Processing & Management, May 2016

   Emotion and Sentiment in Social and Expressive Media

   Abs Bib

   In this paper, we analyze the influence of Twitter users in sharing news articles that may affect the readers’ mood. We collected data of more than 2000 Twitter users who shared news articles from Corriere.it, a daily newspaper that provides mood metadata annotated by readers on a voluntary basis. We automatically annotated personality types and communication styles of Twitter users and analyzed the correlations between personality, communication style, Twitter metadata (such as followig and folllowers) and the type of mood associated to the articles they shared. We also run a feature selection task, to find the best predictors of positive and negative mood sharing, and a classification task. We automatically predicted positive and negative mood sharers with 61.7% F1-measure.

   @article{CELLI201693,
     author = {Celli, Fabio and Ghosh, Arindam and Alam, Firoj and Riccardi, Giuseppe},
     date-modified = {2024-08-03 07:58:24 +0300},
     issn = {0306-4573},
     journal = {Information Processing & Management},
     keywords = {Personality, Communication, Mood detection, Social media, Twitter, Contagion},
     note = {Emotion and Sentiment in Social and Expressive Media},
     number = {1},
     pages = {93-98},
     title = {In the mood for sharing contents: Emotions, personality and interaction styles in the diffusion of news},
     volume = {52},
     year = {2016},
     url = {https://www.sciencedirect.com/science/article/pii/S030645731500103X},
     doi = {https://doi.org/10.1016/j.ipm.2015.08.002},
   }

3. Multilevel Annotation of Agreement and Disagreement in Italian News Blogs

   Celli Fabio, Riccardi Giuseppe, and Alam Firoj

   In Proc. of LREC , May 2016

   Bib

   @inproceedings{Celli2016,
     author = {Fabio, Celli and Giuseppe, Riccardi and Firoj, Alam},
     booktitle = {Proc. of LREC},
     title = {Multilevel Annotation of Agreement and Disagreement in Italian News Blogs},
     year = {2016},
   }