"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF."

Kangwen Zhao et al. (2025)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2505.12843

access: open

type: Informal or Other Publication

metadata version: 2025-06-26

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2505-12843
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2505-12843
Kangwen Zhao, Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Dongyun Xue, Wengang Zhou, Li Li, Houqiang Li:
Bias Fitting to Mitigate Length Bias of Reward Model in RLHF. CoRR abs/2505.12843 (2025)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.