arXiv - CSCL: "Cognitive Dissonance: Why Do Language Model Outpu…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?. (arXiv:2312.03729v1 [cs.CL])

http://arxiv.org/abs/2312.03729 #arXiv #NLProc

Dec 10, 2023, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation