Preference Reasoning under Indeterminacy in Large Language Models
It is argued that indeterminacy, rather than correctness alone, is a central challenge for AI reasoning, and that state-of-the-art language models systematically fail to distinguish between determined and undetermined instances, exhibiting miscalibrated reasoning even in verification settings.
Hadi Hosseini, Samarth Khanna, Xi-Yuan Wang
· 0 citations