{"total":36,"rows":[{"id":"2506.22405","title":"Sequential Diagnosis with Language Models","created":"2025-06-27","cited_by_count":60,"area":null},{"id":"2507.23486","title":"A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains","created":"2025-07-31","cited_by_count":28,"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":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2601.16529","title":"SycoEval-EM: Sycophancy Evaluation of Large Language Models in Simulated Clinical Encounters for Emergency Care","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2509.05878","title":"MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries","created":"2025-09-07","cited_by_count":4,"area":null},{"id":"2507.03152","title":"MedVAL: Toward Expert-Level Medical Text Validation with Language Models","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2511.20836","title":"Structured Prompts Improve Evaluation of Language Models","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2603.02790","title":"Designing UNICORN: a Unified Benchmark for Imaging in Computational Pathology, Radiology, and Natural Language","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2510.00038","title":"DM-Bench: Benchmarking LLMs for Personalized Decision Making in Diabetes Management","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.14254","title":"Generalist vs Specialist Time Series Foundation Models: Investigating Potential Emergent Behaviors in Assessing Human Health Using PPG Signals","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2511.17554","title":"Beyond the Rubric: Cultural Misalignment in LLM Benchmarks for Sexual and Reproductive Health","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2512.19691","title":"Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversight","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2601.04195","title":"MedPI: Evaluating AI Systems in Medical Patient-facing Interactions","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2603.15677","title":"MedArena: Comparing LLMs for Medicine-in-the-Wild Clinician Preferences","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2509.07325","title":"CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2512.09048","title":"Monitoring Deployed AI Systems in Health Care","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2512.20983","title":"Automatic Replication of LLM Mistakes in Medical Conversations","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2601.12227","title":"Learning Longitudinal Health Representations from EHR and Wearable Data","created":"2026-01-18","cited_by_count":1,"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":"2506.18819","title":"RWESummary: A Framework and Test for Choosing Large Language Models to Summarize Real-World Evidence (RWE) Studies","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.19885","title":"Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2509.08087","title":"Performance Assessment Strategies for Language Model Applications in Healthcare","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.04033","title":"A global log for medical AI","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.17764","title":"Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.18880","title":"Towards Better Health Conversations: The Benefits of Context-seeking","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2512.02043","title":"Mirror, Mirror on the Wall -- Which is the Best Model of Them All?","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2605.08685","title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.09765","title":"WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.17765","title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.18999","title":"MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.06080","title":"PhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.28697","title":"LabFactory: Building and Evaluating Executable AI Labs","created":"2026-09-23","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},{"id":"2609.36515","title":"Large-scale factor analysis shows machine intelligence is only partially interpretable","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.18529","title":"How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}