arXiv - CSCL: "The Impact of Preference Agreement in Reinforceme…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

The Impact of Preference Agreement in Reinforcement Learning from Human Feedback: A Case Study in Summarization. (arXiv:2311.04919v1 [cs.CL])

http://arxiv.org/abs/2311.04919 #arXiv #NLProc

Nov 12, 2023, 03:17 · · arxiv-cscl · · ·

Sign in to participate in the conversation