"RRM: Robust Reward Model Training Mitigates Reward Hacking."

Tianqi Liu et al. (2024)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2409.13156

access: open

type: Informal or Other Publication

metadata version: 2024-10-18

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2409-13156
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2409-13156
Tianqi Liu, Wei Xiong, Jie Ren, Lichang Chen, Junru Wu, Rishabh Joshi, Yang Gao, Jiaming Shen, Zhen Qin, Tianhe Yu, Daniel Sohn, Anastasiia Makarova, Jeremiah Z. Liu, Yuan Liu, Bilal Piot, Abe Ittycheriah, Aviral Kumar, Mohammad Saleh:
RRM: Robust Reward Model Training Mitigates Reward Hacking. CoRR abs/2409.13156 (2024)

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.