Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs
It is demonstrated that when producing deceptive rather than honest responses, models exhibit a gap between their belief and their commitment, which shows how confidence can be a practical tool for detecting and diagnosing deceptive behaviour in LLMs.
Ali Asad, Stephen Obadinma, Anshul Pattoo et al.
· 0 citations