Biography

Hou Pong (Ken) Chan is an Assistant Professor in the Department of Artificial Intelligence at the University of Macau. Previously, he was a Research Scientist at Alibaba DAMO Academy, Singapore. He also served as a Macao Fellow at the University of Macau and as a Visiting Postdoctoral Researcher at the University of Illinois Urbana-Champaign (UIUC), where he worked with Prof. Heng Ji.

He received his Ph.D. from The Chinese University of Hong Kong in 2020 under the supervision of Prof. Irwin King. During his doctoral studies, he was also a visiting Ph.D. student at Northeastern University in Spring 2019, where he worked with Prof. Lu Wang.

His research focuses on improving the trustworthiness of large language models (LLMs) and multimodal large language models (MLLMs), particularly by understanding and mitigating hallucinations arising from their perception and reasoning processes.

News

Selected Open-sourced LLMs

I was a core contributor to the development of two open-sourced foundation-model families: Lingshu, a generalist foundation model for unified multimodal medical understanding and reasoning, and SeaLLMs 3, a family of open foundation and chat models for Southeast Asian languages. The Lingshu models have received more than 464,000 downloads on Hugging Face, while SeaLLMs received the Innovate for Impact Use Case Award at the 2024 AI for Good Global Summit.

Publications (* indicates equal contribution) [Google Scholar]

2026

• On the Design Fundamentals of Pixel Text Representation Learning
  Chaohao Yuan, Ruifeng Yuan, Zhuoxu Huang, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026 (Acceptance rate 15.4%).
  

  [code]

• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
  Weiwen Xu*, Hou Pong Chan*, Long Li*, Mahani Aljunied, Ruifeng Yuan, Jianyu Wang, Chenghao Xiao, Guizhen Chen, Chaoqun Liu, Zhaodonghui Li, Yu Sun, Junao Shen, Chaojun Wang, Jie Tan, Deli Zhao, Tingyang Xu, Hao Zhang, Yu Rong.
  To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026.
  

  [project] [models] [evaluation toolkit]

• Understanding the Behaviors of Environment-aware Information Retrieval
  Ruifeng Yuan, Chaohao Yuan, David Dai, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL, Oral), 2026.
  

  [code]

• VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning
  Jingkun Ma, Runzhe Zhan, Derek F. Wong, Yang Li, Di Sun, Hou Pong Chan, Lidia S. Chao.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2026.
  

  [project]

• Large Language Models Do NOT Really Know What They Don't Know
  Chi Seng Cheang, Hou Pong Chan, Wenxuan Zhang, Yang Deng
  Findings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2026.
  

2025

• Scaling Language-Centric Omnimodal Representation Learning
  Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong.
  Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
  
• Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
  Zhe Hu, Jing Li, Zhongzhu Pu, Hou Pong Chan, Yu Yin.
  Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
  
• M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework
  Yew Ken Chia, Liying Cheng, Hou Pong Chan, Chaoqun Liu, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, Lidong Bing.
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025.
  [Project] [Code and data]
• Let's See Clearly: Enhancing Multimodal LLM Reasoning with Better Visual Perception
  Guizhen Chen, Weiwen Xu, Hao Zhang, Hou Pong Chan, Deli Zhao, Anh Tuan Luu, Yu Rong.
  Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), short paper, 2025.
  
• Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations
  Chenghao Xiao, Hou Pong Chan, Hao Zhang, Mahani Aljunied, Lidong Bing, Noura Al Moubayed, Yu Rong.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
  [Code]
• FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
  Guizhen Chen, Weiwen Xu, Hao Zhang, Hou Pong Chan, Chaoqun Liu, Lidong Bing, Deli Zhao, Anh Tuan Luu, Yu Rong.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
  
• ManiTweet: A New Benchmark for Identifying Manipulation of News on Social Media
  Kung-Hsiang Huang, Hou Pong Chan, Kathleen McKeown, Heng Ji.
  Proceedings of International Conference on Computational Linguistics (COLING), 2025.
  
• Persona-db: Efficient large language model personalization for response prediction with collaborative data refinement
  Chenkai Sun, Ke Yang, Revanth Gangi Reddy, Yi R Fung, Hou Pong Chan, Kevin Small, ChengXiang Zhai, Heng Ji.
  Proceedings of International Conference on Computational Linguistics (COLING), 2025.
  
• Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation
  Zhe Hu, Hou Pong Chan, Jing Li, Yu Yin.
  Proceedings of International Conference on Computational Linguistics (COLING), short paper, 2025.
  

2024

• From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models
  Kung-Hsiang Huang, Hou Pong Chan, Yi R. Fung, Haoyi Qiu, Mingyang Zhou, Shafiq Joty, Shih-Fu Chang, Heng Ji.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024.
  

  [project]

• Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning
  Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi R. Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji.
  Findings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2024.
  
• AMERICANO: Argument Generation with Discourse-driven Decomposition and Agent Interaction
  Zhe Hu, Hou Pong Chan, Yu Yin.
  Proceedings of the International Natural Language Generation Conference (INLG), 2024.
  

2023

• Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization
  Chi Seng Cheang, Hou Pong Chan, Derek F Wong, Xuebo Liu, Zhaocong Li, Yanming Sun, Shudong Liu, Lidia S Chao
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
  
• Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting
  Chenkai Sun, Jinning Li, Yi Fung, Hou Pong Chan, Tarek Abdelzaher, ChengXiang Zhai, Heng Ji
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
  
• Zero-shot Faithful Factual Error Correction
  Kung-Hsiang Huang, Hou Pong Chan, Heng Ji
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2023.
  
• Measuring the Effect of Influential Messages on Varying Personas
  Chenkai Sun, Jinning Li, Hou Pong Chan, ChengXiang Zhai, Heng Ji
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), short paper, 2023.
  
• Multimedia Generative Script Learning for Task Planning
  Qingyun Wang, Manling Li, Hou Pong Chan, Lifu Huang, Julia Hockenmaier, Girish Chowdhary, Heng Ji
  Findings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2023.
  
• Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization
  Hou Pong Chan, Qi Zeng, Heng Ji.
  Findings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), short paper, 2023.
  

  [code]

• PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream
  Susik Yoon, Hou Pong Chan, Jiawei Han.
  Proceedings of The Web Conference (WWW), 2023.
  
• SumREN: Summarizing Reported Speech about Events in News
  Revanth Gangi Reddy, Heba Elfardy, Hou Pong Chan, Kevin Small, Heng Ji.
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023.
  

2022

• A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective
  Zhe Hu, Hou Pong Chan, Lifu Huang.
  Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), short paper, 2022.
  
• PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
  Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, and Lifu Huang.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2022.
  
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
  Zhe Hu, Zhiwei Cao, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Jinsong Su, and Hua Wu
  IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2022.
  
• Grounding Commands for Autonomous Vehicles via Layer Fusion with Region-specific Dynamic Layer Attention
  Hou Pong Chan*, Mingxi Guo*, and Cheng-Zhong Xu.
  Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
  

  [code]

2021

• Controllable Summarization with Constrained Markov Decision Process
  Hou Pong Chan, Lu Wang, and Irwin King.
  Transactions of the Association for Computational Linguistics (TACL), 2021.
  
• A Condense-then-Select Strategy for Text Summarization
  Hou Pong Chan and Irwin King.
  Knowledge-Based Systems (KBS), 2021.
  
• Dialogue summarization with supporting utterance flow modelling and fact regularization
  Wang Chen, Piji Li, Hou Pong Chan, and Irwin King.
  Knowledge-Based Systems (KBS), 2021.
  

Before 2021 (Before my PhD graduation)

• A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss
  Hou Pong Chan*, Wang Chen*, and Irwin King.
  Proceedings of the 43th Conference of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2020.
  

  [code]

• Exclusive Hierarchical Decoding for Deep Keyphrase Generation
  Wang Chen, Hou Pong Chan, Piji Li, and Irwin King.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2020.
  

  [code]

• Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards
  Hou Pong Chan, Wang Chen, Lu Wang, and Irwin King.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
  

  [code]

• Topic-Aware Neural Keyphrase Generation for Social Media Language
  Yue Wang, Jing Li, Hou Pong Chan, Irwin King, Michael R. Lyu, and Shuming Shi.
  Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
  

  [code]

• An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction
  Wang Chen, Hou Pong Chan, Piji Li, Lidong Bing, and Irwin King.
  Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
  

  [code]

• Thread Popularity Prediction and Tracking with a Permutation-invariant Model
  Hou Pong Chan and Irwin King.
  Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
  
• Leveraging Social Connections to Improve Peer Assessment in MOOCs
  Hou Pong Chan and Irwin King.
  Proceedings of the 26th International Conference on World Wide Web Companion, Digital Learning Track (WWW), 2017.
  
• Trust-aware peer assessment using multi-armed bandit algorithms
  Hou Pong Chan, Tong Zhao, and Irwin King.
  Proceedings of the 25th International Conference on World Wide Web. (WWW), 2016. Workshop on Web Science and Technology for Education.
  

Preprints

• Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate
  Kyungha Kim*, Sangyun Lee*, Kung-Hsiang Huang*, Hou Pong Chan, Manling Li, Heng Ji.
  

Honors & Awards

Outstanding Senior Area Chair Award, AACL, 2025

Outstanding Reviewer, ACL, 2021

Outstanding Reviewer, EMNLP, 2020

The Best Teaching Assistant Award, CSE Department, CUHK, 2018

The Best Teaching Assistant Award, CSE Department, CUHK, 2017

Dean's list, Engineering Faculty, CUHK, 2014

Dean's list, Engineering Faculty, CUHK, 2013

Professional Activities

Publication Co-chair: AACL 2025

Senior Area Chair: AACL 2025

Local Co-chair: MT Summit 2023

Session Chair: ACL 2025 (virtual), ICONIP 2020 Tutorial (virtual)

SPC Member: IJCAI 2021

Conference Reviewer: ACL ARR 2023-2025, IROS 2023, AAAI 2023, EMNLP 2022, ACL 2022, AAAI 2022, EMNLP 2021, ACL 2021, NAACL 2021, AAAI 2021, EMNLP 2020, ACL 2020, AAAI 2020, EMNLP 2019, AAAI 2019

Journal Reviewer: IEEE TKDE, IEEE/ACM TASLP, ACM TALLIP, KBS Journal

Teaching Assistant

2018	Spring	CSCI2100A Data Structures
2017	Fall	CSCI2100 Data Structures
2017	Spring	CSCI3180 Principles of Programming Languages
2016	Spring	CSCI2100A Data Structures
2015	Fall	ENGG2120 Introduction to Digital and Microprocessor Systems