Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
Ziwei Ji, Lei Yu, Yeskendir Koishekenov, Yejin Bang, Anthony Hartshorn, Alan Schelten, Cheng Zhang, Pascale Fung
Abstract
LLMs often adopt an assertive language style also when making false claims. Such ”overconfident hallucinations” mislead users and erode trust. Achieving the ability to express in language the actual degree of uncertainty around a claim is therefore of great importance. We find that ”verbal uncertainty” is governed by a single linear feature in the representation space of LLMs, and shows that this has only moderate correlation with the actual ”semantic uncertainty” of the model. We apply this insight and show that (1) the mismatch between semantic and verbal uncertainty is a better predictor of hallucinations than semantic uncertainty alone and (2) we can intervene on verbal uncertainty at inference time and reduce confident hallucinations on short-form answers, achieving an average relative reduction of ~30%.
BibTeX
@inproceedings{emnlp2025_calibratingverba,
title = {Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations},
author = {Ziwei Ji and Lei Yu and Yeskendir Koishekenov and Yejin Bang and Anthony Hartshorn and Alan Schelten and Cheng Zhang and Pascale Fung and Nicola Cancedda},
booktitle = {EMNLP 2025},
year = {2025}
}