arXiv - CSCL: "Pruning for Protection: Increasing Jailbreak Resi…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning. (arXiv:2401.10862v1 [cs.LG])

http://arxiv.org/abs/2401.10862 #arXiv #NLProc

Jan 22, 2024, 03:20 · · arxiv-cscl · · ·

Sign in to participate in the conversation