The adoption of large language models (LLMs) to assist clinicians has attracted remarkable attention. Existing works mainly adopt the close-ended question-answering (QA) task with answer options for evaluation. However, many clinical decisions involve answering open-ended questions without pre-set options. To better understand LLMs in the clinic, we construct a benchmark ClinicBench. We first collect eleven existing datasets covering diverse clinical language generation, understanding, and reasoning tasks. Furthermore, we construct six novel datasets and clinical tasks that are complex but common in real-world practice, e.g., open-ended decision-making, long document processing, and emerging drug analysis. We conduct an extensive evaluation of twenty-two LLMs under both zero-shot and few-shot settings. Finally, we invite medical experts to evaluate the clinical usefulness of LLMs. The benchmark data is available at https://github.com/AI-in-Health/ClinicBench.
@article{arxiv.2405.00716,
title = {Large Language Models in the Clinic: A Comprehensive Benchmark},
author = {Fenglin Liu and Zheng Li and Hongjian Zhou and Qingyu Yin and Jingfeng Yang and Xianfeng Tang and Chen Luo and Ming Zeng and Haoming Jiang and Yifan Gao and Priyanka Nigam and Sreyashi Nag and Bing Yin and Yining Hua and Xuan Zhou and Omid Rohanian and Anshul Thakur and Lei Clifton and David A. Clifton},
journal= {arXiv preprint arXiv:2405.00716},
year = {2024}
}