一个自动化的框架来评估LLM如何引用相关的医学参考文献
Kevin Wu1, Eric Wu2, Kevin Wei3
1Department of Biomedical Data Science, Stanford University, Stanford, CA, USA.
Nature communications
|April 16, 2025
概括
大型语言模型 (LLM) 往往无法用引用的来源来支持健康声明. 一项新的研究显示,50-90%的LLM回复缺乏足够的来源支持,影响了医疗查询的可信度.
科学领域:
- 医疗保健中的人工智能
- 医疗信息学 医疗信息学
- 自然语言处理自然语言处理.
背景情况:
- 大型语言模型 (LLM) 越来越多地用于与健康有关的调查.
- 确保LLM产生的健康信息得到可靠参考的支持至关重要.
- LLM引用的来源实际支持其主张的程度尚不清楚.
研究的目的:
- 引入SourceCheckup,这是一个用于评估源相关性和LLM响应支持的自动化管道.
- 评估受欢迎的LLM在医学查询中引用的来源的可靠性.
- 量化LLM生成的医疗陈述的来源支持程度.
主要方法:
- 开发了一个基于代理的管道,名为SourceCheckup.
- 通过800个医学问题的数据集,评估了七个受欢迎的LLM.
- 分析了来自LLM对常见医疗查询的响应中的58,000个陈述源对.
主要成果:
- 50%到90%的LLM答案没有得到充分的支持,或者被引用的来源所抵触.
- 即使是先进的模型,如GPT-4o与网络搜索显示大约30%的陈述没有支持.
- 独立的医疗专业评估证实了来源支持不足的发现.
结论:
- 目前的LLM在提供可信的医疗参考方面存在重大局限性.
- 在LLM产生的大量健康信息中,缺乏足够的证据支持.
- 需要进一步开发,以提高LLM在健康相关应用中的可靠性.
更多相关视频
07:50A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
15.7K
09:20Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
Published on: February 23, 2019
8.6K
相关概念视频
Health Literacy
3.9K
Health literacy is an individual's or a community's capacity to comprehend, receive, read, and use relevant healthcare information and services. The World Health Organization (WHO, 2018) defines health literacy as the cognitive and social skills that determine the ability of individuals to gain access to, understand, and use information in ways that promote and maintain good health. As a result, the WHO helps individuals manage long-term health concerns, participate in preventative...
3.9K
Nursing Clinical Information System
709
Nursing Clinical Information System (NCIS)
A Nursing Clinical Information System (NCIS) is a specialized type of healthcare information system tailored to meet the unique needs of nursing practice. It incorporates the principles of nursing informatics to streamline information management and improve the quality of care delivery.
Critical attributes of NCIS include:
A Nursing Clinical Information System (NCIS) is a specialized type of healthcare information system tailored to meet the unique needs of nursing practice. It incorporates the principles of nursing informatics to streamline information management and improve the quality of care delivery.
Critical attributes of NCIS include:
709
Health Information Technology and Healthcare Information System
751
Health Information Technology (HIT)
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
751
Assessing Blood pressure in the Leg
1.6K
Proper measurement of leg blood pressure is a critical skill for healthcare providers, ensuring precise and reliable readings. When performed correctly, this procedure informs patient care and enhances the efficacy of interventions. The following text outlines step-by-step guidelines to measure blood pressure in the leg, providing clarity and ease of understanding for practitioners.
Preparation:
Preparation:
1.6K
Improving Translational Accuracy
2.5K
2.5K
Classification of Illness
7.2K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
7.2K
