Main Research Interests: Natural Language Processing, Large Language Models, Reasoning for LLMs, Interpretability of LLMs
Biography: Liangming Pan is an Assistant Professor at the School of Computer Science, Peking University, and a Researcher at the Institute of Computational Linguistics (ICL) at Peking University. Before joining PKU, he was an Assistant Professor at the College of Information Science, University of Arizona and a Postdoctoral Scholar at the University of California, Santa Barbara (UCSB), advised by William Yang Wang. He received his Ph.D. from the National University of Singapore (NUS) under the supervision of Min-Yen Kan and Tat-Seng Chua. Earlier, he earned an MEng degree from Tsinghua University (advised by Juanzi Li and Jie Tang) and a BEng degree from Beihang University. His main research interests include natural language processing, machine learning, and large language models. He has published over 60 papers in top international conferences and journals, including ACL, EMNLP, NAACL, TACL, COLING, NeurIPS, ICML, AAAI, ACM MM, and WWW. His work has received the SAC Highlights Award at ACL 2025, Best Paper Runner-up at TRL workshop @ NeurIPS 2024, and the Area Chair Award (Question Answering) at IJCNLP-AACL 2023.
Selected Publications:
[1] Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies. Transactions of the Association for Computational Linguistics (TACL), 2024.
[2] Xiaobao Wu, Liangming Pan, Yuxi Xie, Ruiwen Zhou, Shuai Zhao, Yubo Ma, Mingzhe Du, Rui Mao, Anh Tuan Luu, and William Yang Wang. AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge. ACL 2025. (SAC Highlights Award)
[3] Xinyuan Lu, Liangming Pan*, Yubo Ma, Preslav Nakov, and Min-Yen Kan. TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning. TRL Workshop @ NeurIPS 2024. (Best Paper Runner-up)
[4] Liangming Pan, Alon Albalak, Xinyi Wang, William Yang Wang. Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning. Findings of the 2023 Conference on Empirical Methods in Natural Language Processing. EMNLP 2023.
[5] Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov. Fact-Checking Complex Claims with Program-Guided Reasoning. ACL 2023.
[6] Liangming Pan, Wenhu Chen, Min-Yen Kan, William Yang. Attacking Open-domain Question Answering by Injecting Misinformation. AACL-IJCNLP 2023 (Area Chair Award)
[7] Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang. Zero-shot Fact Verification by Claim Generation. ACL 2021.
[8] Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang. Unsupervised Multi-hop Question Answering by Question Generation. NAACL 2021.
[9] Liangming Pan, Yuxi Xie, Yansong Feng, Min-Yen Kan, Tat-Seng Chua. Semantic Graphs for Deep Question Generation. ACL 2020.
[10] Liangming Pan, Jingjing Chen, Jianlong Wu, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Yu-Gang Jiang, Tat-Seng Chua. Multi-modal Cooking Workflow Construction for Food Recipes. ACM MM 2020.
[11] Liangming Pan, Jingjing Chen, Shaoteng Liu, Chong-Wah Ngo, Min-Yen Kan, Tat-Seng Chua. A Hybrid Approach for Detecting Prerequisite Relations in Multi-modal Food Recipes. IEEE Transactions on Multimedia. 2020 Dec 9.
[12] Liangming Pan, Chengjiang Li, Juanzi Li, and Jie Tang. Prerequisite Relation Learning for Concepts in MOOCs. ACL 2017.
