@inproceedings{savelli-etal-2025-malto,
    title = "{MALTO} at {S}em{E}val-2025 Task 3: Detecting Hallucinations in {LLM}s via Uncertainty Quantification and Larger Model Validation",
    author = "Savelli, Claudio  and
      Koudounas, Alkis  and
      Giobergia, Flavio",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.175/",
    pages = "1318--1324",
    ISBN = "979-8-89176-273-2",
    abstract = "Large language models (LLMs) often produce {\{}textit{\{}hallucinations{\}}{\}} {---}factually incorrect statements that appear highly persuasive. These errors pose risks in fields like healthcare, law, and journalism. This paper presents our approach to the Mu-SHROOM shared task at SemEval 2025, which challenges researchers to detect hallucination spans in LLM outputs. We introduce a new method that combines probability-based analysis with Natural Language Inference to evaluate hallucinations at the word level. Our technique aims to better align with human judgments while working independently of the underlying model. Our experimental results demonstrate the effectiveness of this method compared to existing baselines."
}