arXiv - CSCL: "A Baseline Analysis of Reward Models' Ability To …" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift. (arXiv:2311.14743v7 [cs.CL] UPDATED)

http://arxiv.org/abs/2311.14743 #arXiv #NLProc

Jan 25, 2024, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation