1
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
一种新颖的反思式策略自蒸馏方法，让语言模型通过自我反思实现跨领域推理能力提升，无需人工标注。
arXiv:2605.28014v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs…