@inproceedings{nainia-etal-2025-beyond,
    title = "Beyond {BLEU}: Ethical Risks of Misleading Evaluation in Domain-Specific {QA} with {LLM}s",
    author = "Nainia, Ayoub  and
      Vignes-Lebbe, R{\'e}gine  and
      Mousannif, Hajar  and
      Zahir, Jihad",
    editor = "Picazo-Izquierdo, Alicia  and
      Estevanell-Valladares, Ernesto Luis  and
      Mitkov, Ruslan  and
      Guillena, Rafael Mu{\~n}oz  and
      Cerd{\'a}, Ra{\'u}l Garc{\'i}a",
    booktitle = "Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models",
    month = sep,
    year = "2025",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://aclanthology.org/2025.r2lm-1.9/",
    pages = "77--86"
}