Direct Preference Optimization

Alignment Trainingactive

Family of reward-free alignment methods (DPO, KTO, IPO, ORPO, GRPO) that bypass explicit reward model training.

Organizations

Key Papers

First Proposed: 2023 (Rafailov et al.)

Cluster: Alignment Training

Parent Area: RLHF

Organizations3

SEMINAL

Rafailov et al.2023