ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2501.19358
  4. Cited By
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking

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
ArXivPDFHTML

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
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
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