AI RESEARCH
The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models
arXiv CS.LG
•
ArXi:2603.16728v1 Announce Type: new Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompting or reasoning-trained models has become ubiquitous in modern VLM pipelines, yet its effect on UQ reliability remains poorly understood. We show that reasoning consistently degrades the quality of most uncertainty estimates, even when it improves task accuracy.