@inproceedings{kim-yoon-2025-questioning,
    title = "Questioning Our Questions: How Well Do Medical {QA} Benchmarks Evaluate Clinical Capabilities of Language Models?",
    author = "Kim, Siun  and
      Yoon, Hyung-Jin",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Miwa, Makoto  and
      Tsujii, Junichi",
    booktitle = "Proceedings of the 24th Workshop on Biomedical Language Processing",
    month = aug,
    year = "2025",
    address = "Viena, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.bionlp-1.24/",
    pages = "274--296",
    ISBN = "979-8-89176-275-6"
}