对齐（医疗）LLMs以实现（反事实）公平性
Aligning (Medical) LLMs for (Counterfactual) Fairness
AI总结：
本研究提出在知识蒸馏框架内使用偏好优化的模型对齐方法，有效缓解医疗LLMs中的偏见，提升AI医疗决策的公平性。
摘要：
大型语言模型（LLMs）已成为各种医疗和临床决策支持应用的有前景的解决方案。然而，LLMs经常受到不同类型偏见的影响，这可能导致对个人的不公平对待，加剧健康差异，并降低对AI增强医疗工具的信任。为了解决这一重要问题，在本研究中，我们提出了一种新的模型对齐方法，在知识蒸馏框架内使用偏好优化方法对LLMs进行对齐。在介绍我们提出的方法之前，我们首先使用一个评估框架进行全面的（据我们所知规模最大的）实证评估，以揭示用于医疗应用的LLMs中现有偏见的类型和性质。然后，我们提供了一种偏见缓解技术，以减少LLMs输出中由受保护属性识别的不同子群体之间的不公平模式。我们表明，我们的缓解方法在显著减少观察到的偏见模式方面是有效的。我们的代码公开在\url{https://github.com/healthylaife/FairAlignmentLLM}。
英文摘要：
Large Language Models (LLMs) have emerged as promising solutions for a variety of medical and clinical decision support applications. However, LLMs are often subject to different types of biases, which can lead to unfair treatment of individuals, worsening health disparities, and reducing trust in AI-augmented medical tools. Aiming to address this important issue, in this study, we present a new model alignment approach for aligning LLMs using a preference optimization method within a knowledge distillation framework. Prior to presenting our proposed method, we first use an evaluation framework to conduct a comprehensive (largest to our knowledge) empirical evaluation to reveal the type and nature of existing biases in LLMs used for medical applications. We then offer a bias mitigation technique to reduce the unfair patterns in LLM outputs across different subgroups identified by the protected attributes. We show that our mitigation method is effective in significantly reducing observed biased patterns. Our code is publicly available at \url{https://github.com/healthylaife/FairAlignmentLLM}.
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。
