LLM医疗应用可能因输入社会因素加剧健康不平等，新框架可有效缓解此风险。
Mitigating the Risk of Health Inequity Exacerbated by Large Language Models
- 引入种族、性别等非关键社会因素会误导LLM输出
- 框架在多类人群中显著降低医疗决策偏差
- 适合关注AI医疗公平性的研究者与临床开发者
大型语言模型在医疗领域应用前景广阔，尤其在临床试验匹配和医学问答中表现突出。然而，本研究发现，将种族、性别、收入水平、性少数身份、无家可归、文盲、残疾、失业等非决定性社会人口学因素纳入模型输入，可能导致对相关群体的错误甚至有害输出。若广泛部署，此类偏差可能加剧现有健康不平等。为此，我们提出EquityGuard框架，旨在检测并减轻基于LLM的医疗应用中的健康不平等问题。评估结果表明，该框架能有效促进不同人群间的公平医疗结果。
原文摘要 · Abstract (English)
Recent advancements in large language models have demonstrated their potential in numerous medical applications, particularly in automating clinical trial matching for translational research and enhancing medical question answering for clinical decision support. However, our study shows that incorporating non decisive sociodemographic factors such as race, sex, income level, LGBT+ status, homelessness, illiteracy, disability, and unemployment into the input of LLMs can lead to incorrect and harmful outputs for these populations. These discrepancies risk exacerbating existing health disparities if LLMs are widely adopted in healthcare. To address this issue, we introduce EquityGuard, a novel framework designed to detect and mitigate the risk of health inequities in LLM based medical applications. Our evaluation demonstrates its efficacy in promoting equitable outcomes across diverse populations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。