4 papers
Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
Kaizhao Liu, Qi Long, Zhekun Shi +2
Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In thi…
Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
Jiancong Xiao, Zhekun Shi, Kaizhao Liu +2
Despite its empirical success, Reinforcement Learning from Human Feedback (RLHF) has been shown to violate almost all the fundamental axioms in social choice theory -- such as majo…
Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
Zhekun Shi, Kaizhao Liu, Qi Long +2
Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game.…
Diffusion-PINN Sampler
Zhekun Shi, Longlin Yu, Tianyu Xie +1
Recent success of diffusion models has inspired a surge of interest in developing sampling techniques using reverse diffusion processes. However, accurately estimating the drift te…