https://github.com/yjiangcm/bmc
Code for "Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization (ICLR 2025)"
https://github.com/yjiangcm/bmc
alignment dpo rlhf
Last synced: 18 days ago
JSON representation
Code for "Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization (ICLR 2025)"
- Host: GitHub
- URL: https://github.com/yjiangcm/bmc
- Owner: YJiangcm
- License: apache-2.0
- Created: 2024-09-19T07:15:38.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2025-01-26T00:33:07.000Z (8 months ago)
- Last Synced: 2025-01-26T01:25:00.286Z (8 months ago)
- Topics: alignment, dpo, rlhf
- Language: Python
- Homepage: https://arxiv.org/abs/2408.07471
- Size: 180 MB
- Stars: 11
- Watchers: 1
- Forks: 1
- Open Issues: 0