arXiv - CSCL: "RRHF: Rank Responses to Align Language Models wit…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

RRHF: Rank Responses to Align Language Models with Human Feedback without tears. (arXiv:2304.05302v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2304.05302 #arXiv #NLProc

May 23, 2023, 03:07 · · arxiv-cscl · · ·

Sign in to participate in the conversation