构建法语OSCE对话数据集，用可控AI虚拟患者辅助医学生临床训练
A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training
- 基于大模型构建可控制的虚拟患者生成管道，支持真实对话模拟
- 240组对话数据验证了控制模块提升患者真实度与评估一致性
- 系统支持互动练习与自动反馈，适合医学教育场景
医学生临床与沟通能力通常通过客观结构化临床考试（OSCE）评估，这类考试以简短的情景驱动的医患互动模拟为核心。然而，真人标准化患者的数量有限，制约了训练规模，推动了真实虚拟患者（VP）的发展。为此，本文引入一个包含240组学生-患者训练交互的法语OSCE对话数据集，并基于此构建了一个基于大语言模型（LLM）的可控对话生成流水线。该流水线整合了检索式语境对齐与反思循环等模块，确保患者表现的准确性、连贯性与真实性。同时，提出一个多层级评估框架，采用大模型作为评判者（LLM-as-a-Judge），从患者仿真质量、学生表现和语言质量三方面进行评估。实验表明，控制模块普遍提升了患者真实度与学生评估的一致性。最后，我们实现了一个交互式原型系统，学生可与虚拟患者互动并获得自动反馈。
原文摘要 · Abstract (English)
The clinical and communication skills of medical students are commonly assessed through Objective Structured Clinical Examinations (OSCEs), which consist of brief scenario-driven simulations of doctor-patient interactions. However, training is often limited by the low availability of human standardized patients, motivating the development of realistic virtual patients (VPs). To address this gap, we introduce a French OSCE dialogue dataset comprising 240 student-patient training interactions. We build upon it a controllable LLM-based pipeline to generate synthetic OSCE dialogues. The pipeline integrates modular components, such as retrieval-based grounding and a reflection loop, to ensure patient fidelity, coherence, and realism. Additionally, we propose a multi-level evaluation framework assessing patient simulation quality, student performance, and linguistic quality, using an LLM-as-a-Judge approach. Experiments suggest that controllability modules generally improve patient fidelity and student evaluation consistency. Finally, we implement an interactive prototype in which students can practice with a VP and receive automatic feedback.
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。