• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints.

Chaoqi WangYibo JiangChenghao YangHan LiuYuxin Chen
Published in: CoRR (2023)
Keyphrases