@inproceedings{pan-etal-2025-umuteam-semeval,
    title = "{UMUT}eam at {S}em{E}val-2025 Task 3: Detecting Hallucinations in Multilingual Texts Using Encoder-only Models Guided by Large Language Models",
    author = "Pan, Ronghao  and
      Bernal - Beltr{\'a}n, Tom{\'a}s  and
      Garc{\'i}a - D{\'i}az, Jos{\'e} Antonio  and
      Valencia - Garc{\'i}a, Rafael",
    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/transition-to-people-yaml/2025.semeval-1.102/",
    pages = "750--756",
    ISBN = "979-8-89176-273-2",
    abstract = "Large Language Models like GPT-4, LLaMa, Mistral, and Gemma have revolutionized Natural Language Processing, advancing language comprehension, generation, and reasoning. However, they also present challenges, particularly the tendency to hallucinate{---}that is, to produce false or fabricated information. This paper presents our participation in Task 3 Mu-SHROOM of SemEval 2025, which focuses on detecting hallucinations in multilingual contexts. Specifically, the task requires identifying text segments generated by LLMs that correspond to hallucinations and calculating the hallucination probability for each character in the text. To address this challenge, we adopted a token classification approach using the pre-trained XLM-RoBERTa-large model, fine-tuned on the provided training set. Additionally, we integrated context from Llama-3.1-70B to enhance hallucination detection by leveraging its broader and more up-to-date knowledge base. Our approach combines the multilingual capability of XLM-RoBERTa with the contextual understanding of Llama-3.1-70B, producing a detailed hallucination probability for each character in the text. The results demonstrate that our approach consistently outperforms baseline methods across multiple languages, particularly in detecting token-level hallucinations."
}