MedConceal：一个用于在部分可观测性下进行临床隐藏关切推理的基准
MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability
AI总结：
MedConceal通过交互式患者模拟器评估医疗对话中的隐藏关切推理，包含300个案例和600个医生-LLM交互，研究确认和干预能力，发现前沿模型在确认指标上表现优异，而人类医生在干预成功率上表现最佳。
摘要：
患者与医生的沟通是一个信息不对称的问题：患者往往不会透露恐惧、误解或实际障碍，除非医生能够熟练地引导他们表达。有效的医疗对话因此需要在部分可观测性下进行推理：医生必须引导潜在的担忧，通过互动确认它们，并以引导患者接受适当治疗的方式回应。然而，现有的医疗对话基准大多回避这一挑战，通过暴露隐藏的患者状态、将引导简化为提取，或在不建模隐藏内容的情况下评估回应。我们提出了MedConceal，一个包含交互式患者模拟器的基准，用于评估医疗对话中的隐藏担忧推理，包含300个精心编纂的案例和600个医生-LLM交互。该基准基于医生回答的在线健康讨论构建，每个案例将医生可见的上下文与模拟器内部的隐藏担忧配对，这些隐藏担忧源自先前文献并通过专家开发的分类法进行结构化。模拟器将这些担忧隐藏在对话代理之外，跟踪它们是否已被揭示和解决，通过理论基础的回合级沟通信号进行跟踪，并由医生审查以确保临床合理性。这使得能够对任务成功和导致它的交互过程进行过程感知的评估。我们研究了两种能力：确认，通过多轮对话揭示隐藏的担忧，以及干预，解决主要担忧并引导患者朝着目标计划发展。结果表明，没有单一系统主导：前沿模型在不同的确认指标上领先，而人类医生（N=159）在干预成功率上表现最佳。这些结果将隐藏担忧推理在部分可观测性下识别为医疗对话系统的关键未解决挑战。
英文摘要：
Patient-clinician communication is an asymmetric-information problem: patients often do not disclose fears, misconceptions, or practical barriers unless clinicians elicit them skillfully. Effective medical dialogue therefore requires reasoning under partial observability: clinicians must elicit latent concerns, confirm them through interaction, and respond in ways that guide patients toward appropriate care. However, existing medical dialogue benchmarks largely sidestep this challenge by exposing hidden patient state, collapsing elicitation into extraction, or evaluating responses without modeling what remains hidden. We present MedConceal, a benchmark with an interactive patient simulator for evaluating hidden-concern reasoning in medical dialogue, comprising 300 curated cases and 600 clinician-LLM interactions. Built from clinician-answered online health discussions, each case pairing clinician-visible context with simulator-internal hidden concerns derived from prior literature and structured using an expert-developed taxonomy. The simulator withholds these concerns from the dialogue agent, tracks whether they have been revealed and addressed via theory-grounded turn-level communication signals, and is clinician-reviewed for clinical plausibility. This enables process-aware evaluation of both task success and the interaction process that leads to it. We study two abilities: confirmation, surfacing hidden concerns through multi-turn dialogue, and intervention, addressing the primary concern and guiding the patient toward a target plan. Results show that no single system dominates: frontier models lead on different confirmation metrics, while human clinicians (N=159) remain strongest on intervention success. Together, these results identify hidden-concern reasoning under partial observability as a key unresolved challenge for medical dialogue systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
