ETHOS：面向临床多智能体系统的模块化伦理框架
原标题：ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems
AI 摘要
ETHOS 是一个为临床多智能体系统设计的模块化伦理框架，以治理元代理的形式集成到现有系统中，无需改变其底层架构。它通过分层治理（确定性检查、上下文审查和最终伦理批评）在运行时持续评估中间推理步骤和最终输出，以识别伦理风险、请求修订或抑制不符合安全标准的响应。在肝病学临床决策支持系统中的演示表明，ETHOS 通过检测不完整、不一致或超出范围的证据，并在无法支持安全建议时适当增加弃权，提高了决策可靠性。该框架为将高层 AI 伦理原则转化为可部署的保障措施提供了一种实用且可审计的机制。
正文节选
ETHOS : Towards a Modular Ethics Framework for Clinical Multi-Agent Systems Abstract The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and supporting increasingly complex clinical decision-making. However, the deployment of these systems in real-world healthcare settings raises critical ethical concerns related to safety, fairness, accountability, transparency, and patient trust. While nume