Date: September 15, 2025
Type: Advanced Seminar on Law and Technology
Speaker: Yiquan Wu (ZJU-100 Young Professor, Zhejiang University Guanghua Law School)
This talk reviews the trajectory of LegalAI research from task-specific models to LLM-based systems. In its earlier stage, the work focused on automatic trials under a “one model, one task” paradigm, addressing judicial questioning, court’s view generation, and judgment prediction with attention to interpretability and fairness. More recently, the research has shifted toward large legal models, represented by Zhihai-Luwen, which are constructed through continued pretraining, supervised fine-tuning, and retrieval-augmented generation (RAG). These models are further applied through large–small model collaboration and counter-questioning strategies in judicial scenarios. This evolution highlights the shift from narrow automation to general-purpose legal intelligence.
Yiquan Wu is an Assistant Professor (ZJU-100 Young Professor, Doctoral Supervisor) at Zhejiang University. He received his Ph.D. and B.S. degrees from Zhejiang University. His research interests encompass LegalAI, Large Language Models, Natural Language Processing, and Causal Inference. He has published over 20 papers in prestigious conferences and journals such as ACL, EMNLP, NAACL, SIGIR, AAAI, KDD, and WWW.
Moderator: Benjamin Chen, Associate Professor & Director of the Law and Technology Centre, The University of Hong Kong Faculty of Law
