@inproceedings{liu-etal-2024-large,
    title = "Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark",
    author = "Liu, Fenglin  and
      Li, Zheng  and
      Zhou, Hongjian  and
      Yin, Qingyu  and
      Yang, Jingfeng  and
      Tang, Xianfeng  and
      Luo, Chen  and
      Zeng, Ming  and
      Jiang, Haoming  and
      Gao, Yifan  and
      Nigam, Priyanka  and
      Nag, Sreyashi  and
      Yin, Bing  and
      Hua, Yining  and
      Zhou, Xuan  and
      Rohanian, Omid  and
      Thakur, Anshul  and
      Clifton, Lei  and
      Clifton, David A.",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.759/",
    doi = "10.18653/v1/2024.emnlp-main.759",
    pages = "13696--13710"
}