2 results found Sort:
SimPO: Simple Preference Optimization with a Reference-Free Reward
Created
2024-05-21
20 commits to main branch, last one 2 days ago
[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
Created
2023-11-09
14 commits to main branch, last one 17 days ago