Papers
Communities
Events
Blog
Pricing
Search
Open menu
Home
Papers
2501.19358
Cited By
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
31 January 2025
Yuchun Miao
Sen Zhang
Liang Ding
Yuqi Zhang
Lefei Zhang
Dacheng Tao
Re-assign community
ArXiv
PDF
HTML
Papers citing
"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking"
2 / 2 papers shown
Title
Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization
Wenjun Cao
AAML
44
0
0
07 May 2025
A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
Jialun Zhong
Wei Shen
Yanzeng Li
Songyang Gao
Hua Lu
Yicheng Chen
Yang Zhang
Wei Zhou
Jinjie Gu
Lei Zou
LRM
45
2
0
12 Apr 2025
1