Web IR / NLP Group (WING) @ NUS

The Web, Information Retrieval / Natural Language Processing Group (WING) explores the research area of applied language processing and information retrieval to the Web and related technologies. Areas of current interest are question answering, scholarly digital libraries, verb similarity, focused crawling, citation parsing and spidering, web page classification and division, text segmentation, and full text analysis. WING is headed by Min (A/P Min-Yen KAN). We are based in the Computational Linguistics Laboratory of the School of Computing at the National University of Singapore. We often work with the Natural Language Processing Group and the Lab for Media Search. We are part of the Media Technologies research group umbrella.

Latest Conference Publications

(2025). Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines. In Findings of the 63nd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, July 27–August 1st, 2025.

PDF Cite

(2025). What Makes a Good Natural Language Prompt?. In 63nd Annual Meeting of the Association for Computational Linguistics (Volume 1, Long Papers), Vienna, Austria, July 27–August 1st, 2025.

PDF Cite

(2025). LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs. In 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, Albuquerque, New Mexico April 29–May 4, USA, 2025.

PDF Cite

(2025). Aligning Large Language Models with Human Opinions through Persona Selection and Value-Belief-Norm Reasoning. Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025, Abu Dhabi, UAE, January 19-24, 2025.

Cite URL

(2025). DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation. Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025, Abu Dhabi, UAE, January 19-24, 2025.

Cite URL