[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-317002-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-317002-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","a-french-osce-dialogue-dataset-and-controllable-virtual-patient-system-for-clinical-training","A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training","","Clinical and communication skills of medical students are assessed through Objective Structured Clinical Examinations (OSCEs) that simulate brief doctor–patient interactions. Limited access to human standardized patients motivates realistic virtual patients. The document introduces a French OSCE dialogue dataset with 240 recorded training interactions and a controllable LLM-based pipeline to generate synthetic dialogues. Modular retrieval grounding and a reflection loop target patient fidelity, coherence, and realism, followed by multi-level LLM-as-a-Judge evaluation and an interactive prototype with automatic feedback.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-french-osce-dialogue-dataset-and-controllable-virtual-patient-system-for-clinical-training/317002/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-french-osce-dialogue-dataset-and-controllable-virtual-patient-system-for-clinical-training/317002.png","ImageObject",300,407,{"name":42,"@type":43},"Aria Callaghan","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-22","2026-09-20",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",19,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the document address in OSCE training?","Question",{"text":63,"@type":64},"OSCE training is constrained by limited availability of human standardized patients and evaluators, creating scalability and cost issues for repeated practice.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What does the proposed dataset contain?",{"text":68,"@type":64},"The dataset includes 240 recorded and transcribed French OSCE student–patient training interactions.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the controllable LLM-based pipeline improve virtual patient quality and assessment?",{"text":72,"@type":64},"It uses modular retrieval-based grounding and a reflection loop to improve patient fidelity and realism, and it supports a multi-level LLM-as-a-Judge evaluation framework to assess patient simulation quality, student performance, and linguistic quality.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},317002,1790106286,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},962084926284,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training  \nDoria Bonzi 1 , Tom Bourgeade 1 , Fabrice Lef`evre2 , Irina Illina 1  \n1 Lorraine Universit´e, CNRS, Inria, LORIA, Nancy, France  \n2 Avignon Universit´e, LIA, UPR 4128, Avignon, France [doria. bonzi@loria. fr](doria. bonzi@loria. fr) , [tom. bourgeade@loria. fr](tom. bourgeade@loria. fr) , [irina. illina@loria. fr](irina. illina@loria. fr)  \n[fabrice. lefevre@univ-avignon. fr](fabrice. lefevre@univ-avignon. fr)  \narXiv :2606 .28526v1 [ cs .CL] 26 Jun 2026  \nAbstract  \nThe clinical and communication skills of medical students are commonly assessed through Objective Structured Clinical Examinations (OSCEs), which consist of brief scenario-driven simulations of doctorpatient 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  \n240 student–patient training interactions. We build upon it a controllable LLMbased 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 also implement an interactive prototype in which students can practice with a VP and receive automatic feedback.  \n1 Introduction  \nObjective Structured Clinical Examinations (OSCEs) are used to assess both clinical reasoning and communication skills in medical education. In France, these exams involve medical students playing the role of a physician in 7 to 10-minute scenario-based simulated interactions with a standardized patient (SP), under the observation of an evaluator. A SP is defined as a trained individual who portrays a predefined patient scenario for the training and assessment of healthcare  \nstudents (Lewis et al. , 2017) . Each OSCE scenario is referred to as a “station,” and can cover various medical interactions, ranging from patient history taking and analyzing results to breaking bad news. By design, OSCEs approximate real clinical encounters and intentionally simplify many aspects for pedagogical purposes. Communication skills play a central role in OSCE performance; however, student training is limited by the availability of human standardized patients and evaluators, leading to scalability and cost issues for repeated practice.  \nVirtual Patient (VP) systems have been proposed to address these problems, relying on rule-based or script-driven approaches (Ziniet al. , 2019; Campillos-Llanos et al. , 2019; Laleye et al. , 2020a) . Data-driven and LLMbased VP systems have demonstrated improved fluency and realism (Voigt et al. , 2025; Garc´ıa-Torres et al. , 2024; Cook et al. , 2025) . Some studies explored automated feedback for OSCE assessments using LLM-as-a-Judge (Shakur et al. , 2024; Campbell et al. , 2025; Huang et al. , 2026) . Despite these advances, current LLM-based VP systems often lack controllability, hindering consistent adherence to predefined clinical stations. Recent work has also highlighted the lack of standardized and reproducible evaluation frameworks in LLMbased VP systems (Li and Lutfi, 2026), essential for reliable assessment.  \nPublicly available OSCE-related datasets are rare, especially in French. Existing OSCE datasets in English focus on specific clinical tasks or domains (Fareez et al. , 2022; Saleyet al. , 2024) . Large-scale medical dialogue resources (Liu et al. , 2024; Ben Abacha et al. , 2023) are generally not aligned with OSCE constraints or lack the interactional and evaluative structu","cbCaih0yxRhIWYWG","https://ap.wps.com/l/cbCaih0yxRhIWYWG","pdf",1240778,18,"English","# Abstract\n# 1 Introduction\n# 2 Related work","[{\"question\":\"What problem does the document address in OSCE training?\",\"answer\":\"OSCE training is constrained by limited availability of human standardized patients and evaluators, creating scalability and cost issues for repeated practice.\"},{\"question\":\"What does the proposed dataset contain?\",\"answer\":\"The dataset includes 240 recorded and transcribed French OSCE student–patient training interactions.\"},{\"question\":\"How does the controllable LLM-based pipeline improve virtual patient quality and assessment?\",\"answer\":\"It uses modular retrieval-based grounding and a reflection loop to improve patient fidelity and realism, and it supports a multi-level LLM-as-a-Judge evaluation framework to assess patient simulation quality, student performance, and linguistic quality.\"}]","A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training | PDF",1789927544,45]