一作ACL 2026Poster· Natural Language Processing
Quantifying and Understanding Uncertainty in Large Reasoning Models
Yangyi Li · Chenxu Zhao · Mengdi Huai
摘要
Large Reasoning Models (LRMs) have recently demonstrated significant improvements in complex reasoning. While quantifying generation uncertainty in LRMs is crucial, traditional methods are often insufficient because they do not provide finite-sample guarantees for reasoning-answer generation. Con...