arXiv - CSCL: "Fine-tuning Aligned Language Models Compromises S…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!. (arXiv:2310.03693v1 [cs.CL])

http://arxiv.org/abs/2310.03693 #arXiv #NLProc

Oct 08, 2023, 03:17 · · arxiv-cscl · · ·

Sign in to participate in the conversation