报告时间：2026年11月5日上午11:00

报告地点：软件学院B7-303会议室

主持人：蔡毅教授

报告人：Professor Yulan He（何瑜岚教授）

Title: Towards LLMs that Understand, Remember, and Adapt to Users

Abstract:

Large language models (LLMs) are trained on the collective knowledge of the internet, but they are used to serve billions of individual users. Recent years witness increasing interests in adapting population-level LLMs to accommodate the diverse goals, preferences, and contexts of individual users. To build personalised LLMs, we need models that can understand users, maintain memory over time, learn from sparse and heterogeneous personal data, and align with what each user values. In this talk, I will illustrate how each of these challenges can be addressed through examples from our group’s recent work. I will conclude by discussing open problems and potential directions for personalised LLM research.

Introduction:

Yulan He is a Professor in Natural Language Processing at King’s College London and a Turing AI Fellow. Her research focuses on improving the robustness of Large Language Model (LLM) reasoning, agentic AI, model interpretability, safety alignment, and the applications of AI in education and health. She has received several awards for her research. Her five-year Turing AI Fellowship project was awarded the Best Research Project (Research Excellence) at the RAi UK AI & Robotics Awards 2026.  She also received a Best Research Paper Award at the same awards ceremony. In addition, she is the recipient of a SWSA Ten-Year Award and a CIKM Test-of-Time Award.