avatar

Fanxiao Li (李钒效)

Ph.D. Student
Yunnan University
lifanxiao15@outlook.com


Welcome to Fanxiao’s Homepage!

I am currently pursuing my Ph.D. at Yunnan University , supervised by Prof. Wei Zhou. I am also a Visiting Ph.D. Student at the National University of Singapore (NUS), supported by CSC scholarship (Sep 2025 – Sep 2026), working with Prof. Min-Yen Kan and Jiaying at NUS Web IR / NLP Group (WING).

💡 Research Interests

My research interests focus on trustworthy social intelligence, with an emphasis on the reliable perception, safe interaction, and trustworthy decision-making of agentic systems in complex social information environments, as well as the detection and governance of mis/disinformation. My research includes:

🔥 News

  • [Apr. 2026] Three papers accepted to ACL 2026 Main!
  • [Jan. 2026] One paper accepted to ICLR 2026!
  • [Jan. 2026] I presented our work at SSNLP!
  • [Nov. 2025] One paper accepted to AAAI 2026! Let's connect in Singapore!
  • [Sep. 2025] I started my visiting at WING!
  • [May. 2025] One paper accepted to ACL 2025!
  • [Jan. 2025] One paper accepted to NAACL 2025!


📝 Selected Publications/Preprints

    Please see my Google Scholar for a full, up-to-date list.
    ( * indicates equal contribution, † indicates corresponding author.)

  1. Preprint
    FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
    Fanxiao Li, Jiaying Wu, Tingchao Fu, Natasha Jaques, Wei Zhou, Min-Yen Kan
    arXiv 2605.11514, 2026.
    PDF Code

  2. ACL
    What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews
    Fanxiao Li, Jiaying Wu, Tingchao Fu, Dayang Li, Herun Wan, Wei Zhou, Min-Yen Kan
    The 64rd Annual Meeting of the Association for Computational Linguistics
    ACL 2026
    PDF Code

  3. ACL
    Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation
    Jiaying Wu*, Zihang Fu*, Haonan Wang, Fanxiao Li, Jiafeng Guo, Preslav Nakov, Min-Yen Kan
    The 64rd Annual Meeting of the Association for Computational Linguistics
    ACL 2026
    PDF Code

  4. AAAI
    Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection
    Fanxiao Li, Jiaying Wu, Tingchao Fu, Yunyun Dong, Bingbing Song, Wei Zhou
    The 40th Annual AAAI Conference on Artificial Intelligence
    AAAI 2026
    PDF Code

  5. ICLR
    Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
    Jiaying Wu, Fanxiao Li, Zihang Fu, Min-Yen Kan, Bryan Hooi
    The Fourteenth International Conference on Learning Representations
    ICLR 2026
    PDF Code

  6. ACL Findings
    CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection
    Fanxiao Li, Jiaying Wu, Canyuan He, Wei Zhou
    The 63rd Annual Meeting of the Association for Computational Linguistics
    ACL Findings 2025
    PDF Code

  7. NAACL
    IMRRF: Integrating Multi-Source Retrieval and Redundancy Filtering for LLM-based Fake News Detection
    Dayang Li, Fanxiao Li, Bingbing Song, Li Tang, Wei Zhou
    2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics
    NAACL 2025
    PDF Code

📋 Service

Conference Reviewer / PC Member

🎖 Honors and Awards

📖 Educations

💻 Internships


Powered by Jekyll and Minimal Light theme.