arxiv
PublishedJuly 31, 2026 at 4:00 AM
—neutral
Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory
Publisher summary· verbatim
arXiv:2603.25112v3 Announce Type: replace-cross Abstract: Standard evaluation of LLM confidence relies on calibration metrics (ECE, Brier score) that conflate two capacities: how much a model knows (Type-1 accuracy) and how well its confidence signal tracks that knowledge (Type-2 metacognitive sensi
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivFRAC-MAS: A Safe and Explainable Multi-Agent System for Fracture Diagnosis14harxivEvaluating the Hidden Costs of Personalization in Large Language Models14harxivStratified Consistency Distillation for Natural Language Formalization14harxivAdversarial Trust Poisoning in Vehicular Collaborative Perception14hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗