用多智能体辩论机制实现可解释、可干预的个性化护理计划生成
Adaptive Arena-based Contestable Argumentative Network-of-Experts for Open-Ended Care Plan Coordination
- 构建基于辩论框架的专家协作系统，动态匹配角色并生成支持与反驳论点
- 在两个数据集上验证，医学微调模型+辩论结构显著提升临床正确性与安全性
- 支持人工介入修改，结果可追溯且逻辑透明，适合医疗决策场景
护理计划协调需整合多专业领域的临床、功能及心理社会信息，而传统大模型流程缺乏透明性与安全性。本文提出CANOE（Contestable Argumentative Network-of-Experts）——一种多智能体神经符号框架，包含五个模块：复杂度评估、自适应团队招募、基于竞技场的量化双极论证框架（A-QBAF）的角色化辩论计算、人机协同辩论以及护理计划合成。专业化智能体为候选干预措施生成支持与反驳论点；冲突通过竞技场式对抗解决后，可接受度分数在论证图中传播。护理人员可接受、拒绝、编辑或添加论点，系统将确定性重新计算最终方案。在Discharge Me!和MedicalRAG数据集上，使用ROUGE-L、AlignScore、MEDCON F1、FKGL及LLM-as-a-judge评估显示，经医学微调的模型表现最佳，且CANOE的辩论结构提供了可信赖的解释与人类可挑战性。
原文摘要 · Abstract (English)
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.
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。