@inproceedings{kobus-etal-2025-atlantis,
    title = "{ATLANTIS} at {S}em{E}val-2025 Task 3 : Detecting Hallucinated Text Spans in Question Answering",
    author = "Kobus, Catherine  and
      Lancelot, Francois  and
      Martin, Marion - Cecile  and
      Ould Amer, Nawal",
    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-1.145/",
    pages = "1098--1107",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents the contributions of the ATLANTIS team to SemEval-2025 Task 3, focusing on detecting hallucinated text spans in question answering systems. Large Language Models (LLMs) have significantly advanced Natural Language Generation (NLG) but remain susceptible to hallucinations, generating incorrect or misleading content. To address this, we explored methods both with and without external context, utilizing few-shot prompting with a LLM, token-level classification or LLM fine-tuned on synthetic data. Notably, our approaches achieved top rankings in Spanish and competitive placements in English and German. This work highlights the importance of integrating relevant context to mitigate hallucinations and demonstrate the potential of fine-tuned models and prompt engineering."
}