Large Language Models in the Clinic: A Comprehensive Benchmark

TL;DR

This paper introduces ClinicBench, a comprehensive benchmark for evaluating large language models in clinical settings across diverse tasks, including open-ended questions and complex decision-making, with extensive evaluation and expert assessment.

Contribution

The paper constructs a new benchmark with diverse datasets and tasks, including novel complex clinical scenarios, to evaluate LLMs' clinical usefulness comprehensively.

Findings

Twenty-two LLMs evaluated under zero-shot and few-shot settings.

Clinical usefulness assessed by medical experts.

Benchmark data publicly available.

Abstract

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.