arXiv - CSCL: "Evaluating the Instruction-Following Robustness o…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection. (arXiv:2308.10819v3 [cs.CL] UPDATED)

http://arxiv.org/abs/2308.10819 #arXiv #NLProc

Nov 28, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation