Yansong Feng

Beijing, China

prof_pic.jpg

😅

I am an associate professor in the Wangxuan Institute of Computer Technology (former ICST) at Peking University. I am affiliated with the group of Web Information Processing. Before that, I worked with Prof. Mirella Lapata and obtained my PhD from ILCC, School of Informatics at the University of Edinburgh. Prior to Edinburgh, I worked with Prof. Jufu Feng on pattern recognition at Peking University.

My current research focuses on harnessing large language models for social good, to support intelligent applications for people who are in need. We are fortunate to be supported by NSFC, RGC, the MOST and also partners from industry.

I serve as an action editor for Computational Linguistics (2025 -), and senior area chair for ACL Rolling Review (2023 -).

news

Feb 01, 2026 Our papers got accepted by AAAI 2026 and ICLR 2026
Aug 15, 2025 Our papers got accepted by EMNLP 2025
May 15, 2025 Our papers got accepted by ACL 2025.

selected publications

  1. ICLR
    2026
    RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning
    Xiao Liu, Da Yin, Zirui Wu, and 1 more author
    In The Fourteenth International Conference on Learning Representations, 2026
  2. ACL
    2025
    Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books
    Chen Zhang, Jiuheng Lin, Xiao Liu, and 2 more authors
    In Proceedings of the Association for Computational Linguistics: ACL 2025, Jul 2025
  3. ACL
    2025
    Automating Legal Concept Interpretation with LLMs: Retrieval, Generation, and Evaluation
    Kangcheng Luo, Quzhe Huang, Cong Jiang, and 1 more author
    In Proceedings of the Association for Computational Linguistics: ACL 2025, Jul 2025
  4. ACL
    2024
    Teaching Large Language Models an Unseen Language on the Fly
    Chen Zhang, Xiao Liu, Jiuheng Lin, and 1 more author
    In Findings of the Association for Computational Linguistics: ACL 2024, Aug 2024
  5. Lawyer llama technical report
    Quzhe Huang, Mingxu Tao, Chen Zhang, and 5 more authors
    arXiv preprint arXiv:2305.15062, Aug 2023