arXiv - CSCL: "DialCoT Meets PPO: Decomposing and Exploring Reas…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models. (arXiv:2310.05074v3 [cs.CL] UPDATED)

http://arxiv.org/abs/2310.05074 #arXiv #NLProc

Oct 24, 2023, 03:20 · · arxiv-cscl · · ·

Sign in to participate in the conversation