preference-alignment

There are 6 repositories under preference-alignment topic.

princeton-nlp/SimPO
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
Language:Python718 8 7349
zjukg/KnowPAT
[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
Language:Python188 4 1217
junkangwu/beta-DPO
[NeurIPS 2024] Official code of $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
Language:Python33 2 20
Shentao-YANG/Dense_Reward_T2I
Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).
Language:Python31 3 10
junkangwu/Dr_DPO
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
Language:Python7 1 00
BARUDA-AI/Awesome-Preference-Optimization
Survey of preference alignment algorithms
0 0 00