Leveraging LLM Embeddings in Legal Analysis

Date: October 27, 2025 (Monday)

Time: 4pm – 5pm

Venue: Academic Conference Room, 11/F Cheng Yu Tung Tower, The University of Hong Kong

Speaker: Sangchul Park, Associate Professor, Seoul National University School of Law

LLM embeddings are valuable tools for inferring semantic similarity between legally meaningful phrases and sentences, and for tasks such as retrieving or clustering legal texts. However, they are not well-suited for reasoning or completion. Acknowledging both their potential and limitations, this session presents three studies that applied LLM embeddings to: (i) predict investor-state dispute settlement (ISDS) filings, (ii) measure potential regulatory overlap in AI regulations, and (iii) assess trademark similarity.

Sangchul Park is an Associate Professor at Seoul National University School of Law, with a joint appointment in the Interdisciplinary Program in AI and the Department of Mathematical Information Science. His research and teaching focus on AI and law, as well as information and telecommunications law. Before entering academia, he spent over 13 years in private practice, specializing in technology, media, and telecommunications. He completed his JSD at the University of Chicago Law School and his undergraduate studies at Seoul National University.

Moderator: Benjamin Chen, Associate Professor & Director of the Law and Technology Centre, The University of Hong Kong Faculty of Law

To register, please go to https://hkuems1.hku.hk/hkuems/ec_regform.aspx?guest=Y&UEID=103338.  A paper will be circulated in advance and attendees will be expected to have read the paper before the seminar. 

We are applying for a CPD point with the Law Society of Hong Kong.

For inquiries, please contact Ms. Grace Chan at mcgrace@hku.hk / 3917 4727.