Human or LLM as Standardized Patients? A Comparative Study for Medical Education
Not on the map. Why?
Abstract (arXiv)
Standardized patients (SPs) are indispensable for clinical skills training but remain expensive and difficult to scale. Although large language model (LLM)-based virtual standardized patients (VSPs) have been proposed as an alternative, their behavior remains unstable and lacks rigorous comparison with human standardized patients. We propose EasyMED, a multi-agent VSP framework that separates case-grounded information disclosure from response generation to support stable, inquiry-conditioned patient behavior. We also introduce SPBench, a human-grounded benchmark with eight expert-defined criteria for interaction-level evaluation. Experiments show that EasyMED more closely matches human SP behavior than existing VSPs, particularly in case consistency and controlled disclosure. A four-week controlled study further demonstrates learning outcomes comparable to human SP training, with stronger early gains for novice learners and improved flexibility, psychological safety, and cost efficiency.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 71 references that are in the map. First posted on arXiv 12 Nov 2025.
Builds on
20 of 71 references.
References · 20
- 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
- 2020Aligning AI With Shared Human Valuescited by 723
- 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
- 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 325
- 2024Large Language Models for Education: A Survey and Outlookcited by 188
- 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 180
- 2025A Survey of LLM-based Agents in Medicine: How far are we from Baymax?cited by 85
- 2023NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classescited by 79
- 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
- 2024Factual Confidence of LLMs: on Reliability and Robustness of Current Estimatorscited by 61
- 2023Large Language Models in Education: Vision and Opportunitiescited by 54
- 2025Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactionscited by 40
8 more
- 2024Large Language Models for Education: A Surveycited by 34
- 2024LLMs Can Simulate Standardized Patients via Agent Coevolutioncited by 22
- 2024Leveraging Large Language Model as Simulated Patients for Clinical Educationcited by 21
- 2025Multimodal Large Language Models for Medicine: A Comprehensive Surveycited by 16
- 2025Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizationscited by 14
- 2024PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluationcited by 10
- 2025Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Trainingcited by 9
- 2025Modeling Challenging Patient Interactions: LLMs for Medical Communication Trainingcited by 7
Built on by
Citing papers per year: 2026: 2.
2 papers.