{"total":24,"rows":[{"id":"2505.17818","title":"PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions","created":"2025-05-23","cited_by_count":32,"area":null},{"id":"2406.17675","title":"Evaluating Large Language Models with Psychometrics","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2502.02802","title":"Consistent Client Simulation for Motivational Interviewing-based Counseling","created":"2025-02-05","cited_by_count":14,"area":null},{"id":"2502.18673","title":"Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizations","created":"2025-02-25","cited_by_count":14,"area":null},{"id":"2601.03023","title":"MedDialogRubrics: A Comprehensive Benchmark and Evaluation Framework for Multi-turn Medical Consultations in Large Language Models","created":"2026-01-06","cited_by_count":12,"area":null},{"id":"2501.08769","title":"Enhanced Large Language Models for Effective Screening of Depression and Anxiety","created":"2025-01-15","cited_by_count":9,"area":null},{"id":"2411.13902","title":"PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation","created":"2024-11-21","cited_by_count":8,"area":null},{"id":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2601.12661","title":"MedConsultBench: A Full-Cycle, Fine-Grained, Process-Aware Benchmark for Medical Consultation Agents","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2601.13918","title":"AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2602.11684","title":"PatientHub: A Unified Framework for Patient Simulation","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2604.04325","title":"Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2508.18905","title":"Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2510.12224","title":"MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2504.15330","title":"Med-CoDE: Medical Critique based Disagreement Evaluation Framework","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2601.10951","title":"Multi-Stage Patient Role-Playing Framework for Realistic Clinical Interactions","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2606.17441","title":"Patients With Personality: Realistic Patient Simulation through Controlled Diversity and Selective Disclosure","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2602.01995","title":"Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowledge Graphs","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.02097","title":"ClinConsensus: A Physician-Calibrated Benchmark for Evaluating Clinical Rubric Coverage in Chinese Medical LLMs","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.10441","title":"VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.12210","title":"Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.14137","title":"From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2609.31607","title":"Statistical attribute alignment for black-box generative AI via output post-processing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38480","title":"KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}