@inproceedings{ji-etal-2025-calibrating,
    title = "Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations",
    author = "Ji, Ziwei  and
      Yu, Lei  and
      Koishekenov, Yeskendir  and
      Bang, Yejin  and
      Hartshorn, Anthony  and
      Schelten, Alan  and
      Zhang, Cheng  and
      Fung, Pascale  and
      Cancedda, Nicola",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.187/",
    pages = "3769--3793",
    ISBN = "979-8-89176-332-6",
    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 {\textasciitilde}30{\%}."
}