{"total":18,"rows":[{"id":"2604.27470","title":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","created":"2026-04-30","cited_by_count":26,"area":null},{"id":"2507.17717","title":"From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes","created":"2025-07-23","cited_by_count":4,"area":null},{"id":"2508.05452","title":"LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.01103","title":"Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2607.25675","title":"DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2607.08257","title":"MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","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":"2603.23506","title":"Leveraging Computerized Adaptive Testing for Cost-effective Evaluation of Large Language Models in Medical Benchmarking","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2603.23514","title":"DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Models","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2605.11398","title":"AcuityBench: Evaluating Clinical Acuity Identification and Uncertainty Alignment","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.00640","title":"TreeProbe : A Tibetan Medicine Benchmark for Cultural Bias in LLMs","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.04514","title":"RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease Management in Respiratory Specialty Care","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.22713","title":"A Source-Grounded Framework for Constructing and Evaluating Progressive Multimodal Diagnostic Dialogues from Clinical Case Reports","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.29582","title":"SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.20827","title":"DischargeBench: Pre-Deployment Evaluation of LLM Discharge Educators through Persona-Grounded Patient Simulation","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.32740","title":"AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}