面向开放式护理计划协调的自适应竞技场式可争议专家论证网络
Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordination
浏览论文内容
中文总结 AI 辅助
针对开放式护理计划协调中单一LLM流程的不足，提出多Agent神经符号框架CANOE，经医学微调模型在相关数据集上表现出强临床正确性，且CANOE具备可解释性与人类可争议性。
中文摘要 AI 辅助
护理计划协调需要综合跨多个专业学科的临床、功能和社会心理异质性信息，而单一的大语言模型（LLM）流程无法以透明或安全的方式完成此项工作。本文提出CANOE（Contestable Argumentative Network-of-Experts，可争议专家论证网络），这是一种多Agent神经符号框架，通过五个模块解决上述局限：复杂度评估、自适应团队招募、基于竞技场的定量双极论证框架（A-QBAF）的角色化论证计算、人在回路中的争议处理以及护理计划合成。角色专业化的Agent为候选干预措施生成支持与攻击论证；冲突通过竞技场式冲突解决机制化解，随后可接受性分数在论证图中传播。护理规划人员可接受、拒绝、编辑或添加论证，框架将确定性地重新计算最终计划。在Discharge Me!和MedicalRAG数据集上，通过ROUGE-L、AlignScore、MEDCON F1、FKGL及大语言模型评审评估显示，经医学微调的模型实现了最强的临床正确性与安全性，而CANOE的论证结构提供了忠实解释与人类可争议性。
英文摘要
Care plan coordination demands synthesizing heterogeneous clinical, functional, and psychosocial information across multiple professional disciplines, where monolithic LLM pipelines cannot perform in a transparent or safe manner. We present CANOE (Contestable Argumentative Network-of-Experts), a multi-agent neuro-symbolic framework that addresses these limitations through five modules: complexity assessment, adaptive team recruitment, role-based argumentative computation via an Arena-based Quantitative Bipolar Argumentation Framework (A-QBAF), human-in-the-loop contestation, and care-plan synthesis. Role-specialized agents generate supporting and attacking arguments for candidate interventions; conflicts are resolved through arena-based clash resolution before acceptability scores propagate across the argumentation graph. Care planners may accept, reject, edit, or add arguments, and the framework will deterministically recompute the final plan. Evaluation on Discharge Me! and MedicalRAG using ROUGE-L, AlignScore, MEDCON F1, FKGL, and LLM-as-a-judge shows that medically fine-tuned models achieve the strongest clinical correctness and safety, while CANOE's argumentative structure provides faithful explanation and human contestability.
发表机构
- University of New Brunswick（新不伦瑞克大学）
- National Research Council Canada（加拿大国家研究委员会）
机构由 AI 辅助整理，请以论文原文为准。
