SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory 事件

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory arXiv:2511.16275v4 Announce Type: replace Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when uncertain, thereby avoiding hallucinations, i.e., plausible yet factually incorrect responses. However, while semantic UQ methods have achieved advanced performa