arXiv - CSCL: "Math-Shepherd: Verify and Reinforce LLMs Step-by-…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations. (arXiv:2312.08935v2 [cs.AI] UPDATED)

http://arxiv.org/abs/2312.08935 #arXiv #NLProc

Dec 31, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation