AI-Fun & ELLIS Invited Speaker Series | Chengchun Shi
| Dates: | 12 November 2025 |
|---|
| Times: | 11:00 - 12:00 |
|---|
| What is it: | Seminar |
|---|
| Organiser: | Faculty of Science and Engineering |
|---|
| Who is it for: | University staff, External researchers, Alumni, Current University students |
|---|
|
Dear all,
November’s AI-Fun and ELLIS Invited Speaker lecture will take place in Nancy Rothwell Building room 3A.012. This is in Core 1, on the third floor. If you go by stairs, once you get to the third floor stairwell/seating area, .012 is the first room on the right (entrance down the corridor on the right). If you use the left, head left out of the lift and room .012 is ahead of you on the left (entrance down the corridor on the right).
November’s speaker is Chengchun Shi from the London School of Economics.
Bio: Chengchun is an associate professor of data science at London School of Economics and Political Science (LSE). Chengchun completed his PhD in Statistics at North Carolina State University before moving to LSE as assistant professor of data science. Chengchun has received the Peter Gavin Hall Institute of Mathematical Statistics (IMS) Early Career Prize, IMS Tweedie Award and the Royal Statistical Society (RSS) Research Prize.
Talk Title: Doubly Robust Alignment for Large Language Models
Abstract: This talk focuses on reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the underlying preference model (e.g., the Bradley-Terry model), the reference policy, or the reward function, resulting in undesirable fine-tuning. To address model misspecification, we propose a doubly robust preference optimization algorithm that remains consistent when either the preference model or the reference policy is correctly specified (without requiring both). Our proposal demonstrates superior and more robust performance than state-of-the-art algorithms, both in theory and in practice. The code is available at https: //github.com/DRPO4LLM/DRPO4LLM
In-person attendance is encouraged but if you can only join online, you are welcome to register via Ticket Source (link provided on this page).
Travel and Contact Information
Find event
3A.012
Nancy Rothwell Building
Booth Street East
Manchester
