arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.03744cs.AI
收藏

MedSafetyBench:评估与改进大型语言模型的医疗安全性

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models

Harvard University(哈佛大学);University of Virginia(弗吉尼亚大学)

Tessa Han, Aounon Kumar, Chirag Agarwal, Himabindu Lakkaraju

AI总结:

本研究基于美国医学协会伦理原则定义了LLMs医疗安全概念,提出首个基准数据集MedSafetyBench,用于评估和改进大模型的医疗安全性,并证明微调可提升安全性且不损失性能。

摘要:

随着大型语言模型(LLMs)发展出日益复杂的能力并应用于医疗环境,评估其医疗安全性变得至关重要,因为这对个人与公共健康、患者安全及人权具有深远影响。然而,目前对于LLMs背景下的医疗安全概念知之甚少,更不用说如何评估和改进它。为填补这一空白,我们首先基于美国医学协会制定的《医学伦理原则》定义了LLMs的医疗安全概念。随后,我们利用这一理解引入了MedSafetyBench,这是首个旨在衡量LLMs医疗安全性的基准数据集。我们通过使用MedSafetyBench评估和改进LLMs的医疗安全性,展示了该基准的实用性。结果表明,公开可用的医疗LLMs未能达到医疗安全标准,而使用MedSafetyBench对其进行微调,能够在保持其医疗性能的同时提升医疗安全性。通过引入这一新基准数据集,我们的工作实现了对LLMs医疗安全现状的系统性研究,并推动了该领域的未来工作,为降低LLMs在医学中的安全风险铺平了道路。该基准数据集和代码可在https://github.com/AI4LIFE-GROUP/med-safety-bench获取。

英文摘要:

As large language models (LLMs) develop increasingly sophisticated capabilities and find applications in medical settings, it becomes important to assess their medical safety due to their far-reaching implications for personal and public health, patient safety, and human rights. However, there is little to no understanding of the notion of medical safety in the context of LLMs, let alone how to evaluate and improve it. To address this gap, we first define the notion of medical safety in LLMs based on the Principles of Medical Ethics set forth by the American Medical Association. We then leverage this understanding to introduce MedSafetyBench, the first benchmark dataset designed to measure the medical safety of LLMs. We demonstrate the utility of MedSafetyBench by using it to evaluate and improve the medical safety of LLMs. Our results show that publicly-available medical LLMs do not meet standards of medical safety and that fine-tuning them using MedSafetyBench improves their medical safety while preserving their medical performance. By introducing this new benchmark dataset, our work enables a systematic study of the state of medical safety in LLMs and motivates future work in this area, paving the way to mitigate the safety risks of LLMs in medicine. The benchmark dataset and code are available at https://github.com/AI4LIFE-GROUP/med-safety-bench.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑