arXiv - CSCL: "Nano: Nested Human-in-the-Loop Reward Learning fo…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control. (arXiv:2211.05750v3 [cs.CL] UPDATED)

http://arxiv.org/abs/2211.05750 #arXiv #NLProc

Sep 26, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation