Saved in:
Bibliographic Details
Main Authors: Ji, Ziwei, Yu, Lei, Koishekenov, Yeskendir, Bang, Yejin, Hartshorn, Anthony, Schelten, Alan, Zhang, Cheng, Fung, Pascale, Cancedda, Nicola
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.14477
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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 show 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%.