1
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
DPO统一范式Uni-DPO，动态优化LLM偏好，解决数据质量差异问题。
arXiv:2506.10054v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a cornerstone of reinforcement learning …