Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values

ArXi:2605.28170v1 Announce Type: new As large language models (LLMs) are increasingly integrated into high-stakes decision-making, the ability to reliably quantify uncertainty has become a critical requirement for safety and trust. However, current uncertainty quantification methods primarily operate at the output level, often failing to distinguish whether uncertainty arises from the model's lack of knowledge or from ambiguity in the user's input.