提出EthosAgents框架，让医疗大模型更好回应多元价值观。
Pluralistic Alignment for Healthcare: A Role-Driven Framework
- 用角色驱动模拟不同文化与情境下的价值观念。
- 在七种模型上验证，提升三类模式的多元对齐效果。
- 适合医疗等高风险领域，关注模型价值多样性。
随着大语言模型在医疗等敏感领域日益应用，确保其输出反映跨群体的多元价值观至关重要。然而，现有对齐方法（如模块化多元主义）在医疗场景中常因个人、文化及情境因素而失效。为此，我们提出首个轻量级、可泛化的多元对齐框架EthosAgents，通过角色模拟多样价值观。实证表明，该方法在七种不同规模的开放与闭源模型上，均有效提升了三种模式的多元对齐表现。研究揭示医疗多元性需要具备适应性与规范意识的方法，为高风险领域中的模型多样性尊重提供了新思路。
原文摘要 · Abstract (English)
As large language models are increasingly deployed in sensitive domains such as healthcare, ensuring their outputs reflect the diverse values and perspectives held across populations is critical. However, existing alignment approaches, including pluralistic paradigms like Modular Pluralism, often fall short in the health domain, where personal, cultural, and situational factors shape pluralism. Motivated by the aforementioned healthcare challenges, we propose a first lightweight, generalizable, pluralistic alignment approach, EthosAgents, designed to simulate diverse perspectives and values. We empirically show that it advances the pluralistic alignment for all three modes across seven varying-sized open and closed models. Our findings reveal that health-related pluralism demands adaptable and normatively aware approaches, offering insights into how these models can better respect diversity in other high-stakes domains.
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。