Litcius/Paper detail

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

Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande, Bruno Castro da Silva

2025ACM Computing Surveys51 citationsDOIOpen Access PDF

Abstract

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 sparse feedback. A categorical review of current literature provides insights for researchers to understand the challenges of RLHF and build upon existing methods.

Topics & Concepts

Computer scienceReinforcement learningHuman–computer interactionArtificial intelligenceReinforcement Learning in RoboticsMulti-Agent Systems and NegotiationEvolutionary Algorithms and Applications
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs | Litcius