ASA Connect

Dear All,

We are excited to announce the Risk Analysis Section May 2026 Webinar!  Please see the below overview and attached flyer for detailed information.

Title: Alignment in Large Language Models: Statistical and Game-Theoretic Perspectives

Speaker: Dr. Weijie Su, Associate Professor, Wharton Statistics and Data Science Department, University of Pennsylvania

Date: May 20, 2026

Time: 2:00PM ET

Registration: https://gsu-edu.zoom.us/webinar/register/WN_mbG7MProTYOeuylaNhQxDA#/registration

Webinar ID: 826 0559 1376

Passcode: 669459

Abstract: Large language models (LLMs) are predominantly aligned with human preferences through reinforcement learning from human feedback (RLHF). In this talk, we explore the theoretical foundations of LLM alignment through the intertwined lenses of statistics and game theory. First, we show how the current formulation of RLHF induces a systematic bias we call preference collapse, and how this can be mitigated by introducing a tailored regularization term into the reward function. Next, we expose a fundamental bottleneck of reward-based alignment, demonstrating that cyclic human preferences cannot be faithfully represented by scalar reward models such as the Bradley-Terry model. More precisely, we establish that such cyclic inconsistencies give rise to a lower bound on the approximation error of any scalar reward fitting. Shifting to a game-theoretic perspective, we focus on Nash learning from human feedback and establish several social choice desiderata for this approach to alignment, including the preservation of preference diversity through the emergence of mixed strategies. Finally, we show that the zero-sum game approach generally cannot perfectly match a target preference distribution as a unique Nash equilibrium.

Thanks,