Representational Control over Self-Report&Behavior Coherence in LLM Risk-Taking
Self-report is an appealing low-cost probe of an LLM's dispositions, but recent work finds only selective agreement between what models report and how they behave. Prior accounts establish these patterns by prompting black-box LLMs, leaving open whether the gap is a prompting artefact or a fact about how the underlying...
R. Kocielnik, Pei-Yang Song, Peng-Rui Han et al.
· 0 citations