@inproceedings{wang-etal-2026-beyond-leaderboard,
    title = "Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models",
    author = "Wang, Wenxuan  and
      Ma, Zizhan  and
      Yu, Guo  and
      Cheung, Yiu-Fai  and
      Ding, Meidan  and
      Liu, Jie  and
      Chen, Wenting  and
      Shen, Linlin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1996/",
    pages = "43078--43123",
    ISBN = "979-8-89176-390-6"
}