2 papers
cs.LG2025
A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
Mengqi Li, Lei Zhao, Anthony Man-Cho So +2
Can a language model improve reasoning by learning from its own imperfect responses, without rewards or teacher-provided solutions? We present Self-evolving Post-Training (SePT), a…
cs.CL2025
DPO-Shift: Shifting the Distribution of Direct Preference Optimization
Xiliang Yang, Feng Jiang, Qianen Zhang +2
Direct Preference Optimization (DPO) and its variants have become increasingly popular for aligning language models with human preferences. These methods aim to teach models to bet…