arXiv - CSCL: "Automatic Hallucination Assessment for Aligned La…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Automatic Hallucination Assessment for Aligned Large Language Models via Transferable Adversarial Attacks. (arXiv:2310.12516v1 [cs.CL])

http://arxiv.org/abs/2310.12516 #arXiv #NLProc

Oct 22, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation