"α-DPO: Adaptive Reward Margin is What Direct Preference Optimization ..."

Junkang Wu et al. (2024)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2410.10148

access: open

type: Informal or Other Publication

metadata version: 2024-11-22

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2410-10148
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2410-10148
Junkang Wu, Xue Wang, Zhengyi Yang, Jiancan Wu, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He:
α-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs. CoRR abs/2410.10148 (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.