RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs

Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari et al.

2025 · ACM Computing Surveys · 44 citations

A significant challenge in training large language models (LLMs) as effective assistants is aligning them with human preferences. Reinforcement learning from human feedback (RLHF) has emerged as a promising solution. However, our understanding of RLHF is often limited to initial design choices. This article analyzes RLHF through reinforcement learning principles, focusing on the reward model. It examines modeling choices and function approximation caveats, highlighting assumptions about reward expressivity and revealing limitations like incorrect generalization, model misspecification, and sp…

Read the paper →

Explore this paper's citation graph on Constellation.