The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

Yuchun Miao; Sen Zhang; Liang Ding; Yuqi Zhang; Lefei Zhang; Dacheng Tao

2025 ICML ICML 2025

The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

🐣 Hot Topic Early Bird - reward hacking

Authors

Yuchun Miao, Sen Zhang, Liang Ding, Yuqi Zhang, Lefei Zhang, Dacheng Tao

Topics

Artificial Intelligence > Core AI > AI Safety Reinforcement Learning > Methods > Deep RL Artificial Intelligence > Core AI > Large Language Models

Keywords

reward hacking contextual relevance energy loss llms eppo final layer

Download PDF