LLMs start overconfident, then swing underconfident when criticized, Nature MI paper finds

ValerioCapraro · x · 2026-09-23

A Nature Machine Intelligence paper identifies two competing biases in LLMs: merely seeing their own earlier answer inflates confidence (a consistency-preserving bias), while criticism flips them from overconfident to underconfident — with direct implications for self-evaluation and self-consistency pipelines.

Related event: Nature MI Study Finds LLMs Overconfident, Then Overcorrect(2 posts)→

Original post →

More from Models

Models channel →