arXiv - CSCL: "Red Teaming Language Models to Reduce Harms: Meth…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned. (arXiv:2209.07858v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2209.07858 #arXiv #NLProc

Nov 24, 2022, 03:14 · · arxiv-cscl · · ·

Sign in to participate in the conversation