3 papers
cs.AI2026
Calibration Is Not Control: Intervention Value for LLM-Agent Oversight
Chubin Zhang, Zhenglin Wan, Xingrui Yu +5
Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can differ in whether intervention helps.…
cs.LG2026
Uncertainty Localization in LLM Reasoning via Embedding Perturbations
Qihao Wen, Jiahao Wang, Yang Nan +3
Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading outputs. For responsible LLM applic…
cs.LG2026
Interpretable Probability Estimation with LLMs via Shapley Reconstruction
Yang Nan, Qihao Wen, Jiahao Wang +4
Large Language Models (LLMs) demonstrate potential to estimate the probability of uncertain events, by leveraging their extensive knowledge and reasoning capabilities. This ability…