Trustworthy Language Models
Dynamic fact-checking, model evaluation, and methods that make language-model decisions more accountable.
Research Fellow at NUSSingapore
Hongzhan Lin 林鸿展
Trustworthy NLP, multimodal reasoning, and social computing.
I am a Research Fellow at the Centre for Trusted Internet and Community (CTIC), National University of Singapore. My work sits at the intersection of natural language processing, multimodal reasoning, and social computing.
Biography
About me
I am Hongzhan Lin (林鸿展), a Research Fellow at the Centre for Trusted Internet and Community (CTIC), National University of Singapore. I work closely with Prof. Mong-Li Lee (Director of CTIC), Prof. Wynne Hsu (Director of IDS), and Prof. Tat-Seng Chua (Director of NExT++).
I received my PhD from the NLP Group at Hong Kong Baptist University in 2026, advised by Prof. Jing Ma. From 2024 to 2025, I was a visiting PhD student at the NExT++ Research Centre at NUS under the guidance of Prof. Tat-Seng Chua.
Before that, I earned my bachelor's and master's degrees from the PRIS Lab at Beijing University of Posts and Telecommunications in 2019 and 2022, advised by Prof. Guang Chen. Earlier in my career, I worked as an NLP research intern at Tencent AI Lab.
Research
Research interests
My work focuses on reliable and interpretable AI systems for language, visual content, and online communities.
Multimodal Reasoning
Reasoning across text and images to understand nuanced, implicit, and potentially harmful online content.
Social Computing
Computational approaches to misinformation, rumors, and the dynamics of information in online communities.
Selected work
Selected publications
2025
ACL 2025
FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models
2024
WWW 2024 (Oral)
Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
2023
AAAI 2023
Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning
2022
NAACL 2022 (Findings)
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning
2021
EMNLP 2021
Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks
Experience
Education and appointments
Research Fellow
Centre for Trusted Internet and Community, National University of Singapore
Visiting PhD Student
NExT++ Research Centre, National University of Singapore
PhD in Computer Science
Hong Kong Baptist University
Master in Artificial Intelligence
Beijing University of Posts and Telecommunications
Academic service
Professional service
Conference organization, area chairing, and peer review.
- Organiser
- ACM WebSci '27, Web & Registration Chair
- Area Chair
- ACL, EMNLP, NeurIPS, AAAI, EACL, AACL
- Conference Reviewer
- ACL, EMNLP, WWW, AAAI, NeurIPS, ICLR, CVPR, NAACL, COLING, ACM MM, IJCAI, ECAI
- Journal Reviewer
- TPAMI, TKDE, TOIS, CL, TOMM, TCSS, TCSVT, TALLIP, JAIR, EAAI, ESWA
Contact