Three Papers Accepted at ACL 2025!
Three of our papers have been accepted at the Association for Computational Linguistics (ACL 2025) — the premier conference in natural language processing and computational linguistics. These works span key areas including annotation methodology, multilingual LLM development, and cultural alignment in question answering.
🌍 NativQA: Culturally-Aligned Multilingual QA
Title: NativQA: Multilingual Culturally-Aligned Natural Query for LLMs Authors: Md. Arid Hasan, Maram Hasanain, Fatema Ahmad, Sahinur Rahman Laskar, Sunaya Upadhyay, Vrunda N Sukhadia, Mucahid Kutlu, Shammur Absar Chowdhury, Firoj Alam Summary: NativQA presents a novel benchmark for multilingual, culturally-grounded, everyday question answering — promoting inclusivity and relevance in LLM applications across diverse global contexts. Preprint: arXiv:2407.09823
🧠 Annotating the Annotators
Title: Annotating the Annotators: Analysis, Insights and Modelling from an Annotation Campaign on Persuasion Techniques Detection Authors: Davide Bassi, Dimitar Iliyanov Dimitrov, Bernardo D’Auria, Firoj Alam, Maram Hasanain, Christian Moro, Luisa Orrù, Gian Piero Turchi, Preslav Nakov, Giovanni Da San Martino Summary: This paper offers a deep dive into annotator behavior and modeling from a large-scale campaign focused on persuasion techniques, providing insights into quality, bias, and strategies for effective human-in-the-loop annotation.
🌐 TituLLMs: Bangla LLMs with Benchmarking
Title: TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking Authors: Shahriar Kabir Nahin, Rabindra Nath Nandi, Sagor Sarker, Quazi Sarwar Muhtaseem, Md Kowsher, Apu Chandraw Shill, Md Ibrahim, Mehadi Hasan Menon, Tareq Al Muntasir, Firoj Alam Summary: We introduce the TituLLMs — a suite of Bangla large language models, accompanied by rigorous benchmarking and dataset development to push the frontier of Bangla NLP. Preprint: arXiv:2502.11187