PACT让AI学会多种诊断思路，避免互相干扰。
PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus
- 用完整病历生成四种诊断对话，限制医生只能看患者可见信息
- 通过分支共识机制，使不同诊断策略互不干扰且效果更优
- 适合需要多角度推理的医疗AI系统开发与评估
临床诊断需在信息不全时灵活运用多种推理范式。现有基于大模型的医疗代理虽具备强推理能力，但单一范式或简单混合对话监督导致各范式难以独立学习且易相互干扰。我们提出PACT（周期性锚点共识训练）框架，结合受控的多范式对话合成与基于共识的分支训练。数据层面，DPS（医生-患者-监督者）利用完整的电子病历进行质量控制，同时确保医生代理仅能访问患者可见信息，生成四种诊断范式下的可信对话，且不泄露隐藏临床答案。训练层面，PACT为每种范式训练一个特定的LoRA分支，并定期通过符号共识将分支聚合为共享锚点。我们进一步构建了动态多轮中文医疗问诊基准用于交互式咨询评估。实验表明，PACT在诊断结果与咨询过程指标上均优于对比的专有、医学专用及任务适配基线模型，达到当前最优水平。
原文摘要 · Abstract (English)
Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information. Existing LLM-based medical agents show strong medical reasoning ability, but single-paradigm or naively mixed dialogue supervision makes these paradigms difficult to learn without interference. We propose \textbf{PACT} (Periodic Anchor Consensus Training), a framework that couples supervised multi-paradigm dialogue synthesis with consensus-based Branch training. At the data level, \textbf{DPS} (Doctor-Patient-Supervisor) uses complete electronic medical records (EMRs) for quality control while keeping the doctor agent restricted to patient-visible information. This produces validated dialogues under four diagnostic reasoning paradigms without leaking hidden clinical answers. At the training level, PACT trains one paradigm-specific LoRA Branch per paradigm and periodically aggregates Branches into a shared Anchor through sign consensus. We further construct a dynamic multi-turn Chinese medical diagnosis benchmark for interactive consultation. Experiments show that PACT achieves state-of-the-art performance among compared proprietary, medical-specialized, and task-adapted baselines on diagnostic outcome and consultation-process metrics.
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。