[Law Tech] Building Trustworthy Legal AI: From Task Automation to Reliable Reasoning

[Law Tech] Building Trustworthy Legal AI: From Task Automation to Reliable Reasoning As Large Language Models (LLMs) reshape access to legal information, they offer unprecedented potential to democratize legal aid for the public. However, transitioning from general text generation to trustworthy legal assistance requires addressing critical challenges at the intersection of legal practice and AI. In this talk, I will walk through our group's recent advancements in Legal AI in tandem with the rise of LLMs, evolving from mitigating hallucinations through domain-specific supervised fine-tuning, to resolving legal ambiguities through dynamic multi-role discussions, grounding generations in formal judicial theories, and eliminating logic flaws in complex legal reasoning using agentic architectures. Finally, I will share my vision for how legal practitioners and AI researchers can collaborate to build actionable, self-verifying legal agents that serve the public. Yansong Feng is an associate professor at the Wangxuan Institute of Computer Technology, Peking University. He received his Ph.D. in Informatics from the University of Edinburgh in 2011. His primary research area is natural language processing, specially harnessing large language models for complex reasoning and supporting intelligent applications for social good. His work has been published in top conferences and journals including ACL, EMNLP, NAACL, TPAMI, AIJ and CL. He was the program co-chair of NLPCC 2021, CCKS 2022 and EMNLP 2023 System Demos, and has served as senior action editor or area chair for ACL ARR, CL, AI&Law, AAAI and *ACL conferences. He has also been the principal investigator or core member for several projects funded by NSFC, MOST's 863 Program/Key R&D Projects and NSF-Beijing. He received the IBM Faculty Award in 2014 and 2015, and the IBM Global Shared University Research Award in 2016. Date/Time: 27/11/2026 16:00-17:00 Venue: Room 824, 8/F Cheng Yu Tung Tower, The University of Hong Kong Organized by: Faculty of Law

Uploaded at 2026/11/03