Controllable Epistemic Sensitivity in Large Language Models: Probing, Benchmarking, and Adaptive Reasoning

摘要

This proposal aims to investigate epistemic uncertainty - uncertainty about knowledge or truth, often conveyed by modals like might or probably in Large Language Models (LLMs). By probing how such cues affect reasoning, we seek to achieve controllable epistemic sensitivity: enabling mod- els to interpret and adapt to uncertainty. Using activation- level analyses and multilingual benchmarks, this work ad- vances transparent, context-aware, and trustworthy reasoning in uncertainty-critical domains.