Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty?

As Large Language Models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial.Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical values.However, it remains unclear whether LLMs reliably use these markers to reflect their intrinsic confidence due to the difficulty of quantifying uncertainty associated with various markers.To address this gap, we first define marker confidence as the observed accuracy when a model employs an epistemic marker.We evaluate its stability across multiple question-answering datasets in both indistribution and out-of-distribution settings for open-source and proprietary LLMs.Our results show that while markers generalize well within the same distribution, their confidence is inconsistent in out-of-distribution scenarios.These findings raise significant concerns about the reliability of epistemic markers for confidence estimation, underscoring the need for improved alignment between marker based confidence and actual model uncertainty.