preference-alignment topic

[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering

zjukg

SimPO: Simple Preference Optimization with a Reference-Free Reward

princeton-nlp

Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).

Shentao-YANG

[NeurIPS 2024] Official code of $\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$

junkangwu