@inproceedings{hailemariam-etal-2025-lcteam,
    title = "{LCT}eam at {S}em{E}val-2025 Task 3: Multilingual Detection of Hallucinations and Overgeneration Mistakes Using {XLM}-{R}o{BERT}a",
    author = "Hailemariam, Araya  and
      Maldonado Rodriguez, Jose  and
      Ba{\c{s}}ar, Ezgi  and
      Kovalev, Roman  and
      Shcharbakova, Hanna",
    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-1.176/",
    pages = "1325--1331",
    ISBN = "979-8-89176-273-2",
    abstract = "In recent years, the tendency of large language models to produce hallucinations has become an object of academic interest. Hallucinated or overgenerated outputs created by LLMs contain factual inaccuracies which can potentially invalidate textual coherence. The Mu-SHROOM shared task sets the goal of developing strategies for detecting hallucinated parts of LLM outputs in a multilingual context. We present an approach applicable across multiple languages, which incorporates the alignment of tokens and hard labels, as well as training a multi-lingual XLM-RoBERTa model. With this approach we managed to achieve 2nd in Chinese and top-10 positions in 7 other language tracks of the competition."
}