@inproceedings{dubanowska-etal-2025-representation,
    title = "Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution",
    author = "Dubanowska, Zuzanna  and
      {\.Z}elaszczyk, Maciej  and
      Brzozowski, Micha{\l}  and
      Mandica, Paolo  and
      Karpowicz, Michal P.",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.952/",
    doi = "10.18653/v1/2025.findings-emnlp.952",
    pages = "17563--17575",
    ISBN = "979-8-89176-335-7",
    abstract = "We critically assess the efficacy of the current SOTA in hallucination detection and find that its performance on the RAGTruth dataset is largely driven by a spurious correlation with data. Controlling for this effect, state-of-the-art performs no better than supervised linear probes, while requiring extensive hyperparameter tuning across datasets. Out-of-distribution generalization is currently out of reach, with all of the analyzed methods performing close to random. We propose a set of guidelines for hallucination detection and its evaluation."
}