{"total":14,"rows":[{"id":"2402.18060","title":"Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions","created":"2024-02-28","cited_by_count":109,"area":null},{"id":"2411.06469","title":"ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?","created":"2024-11-10","cited_by_count":32,"area":null},{"id":"2406.02394","title":"Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2509.18234","title":"The Illusion of Readiness in Health AI","created":"2025-09-22","cited_by_count":12,"area":null},{"id":"2509.16584","title":"From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2411.00024","title":"A Perspective for Adapting Generalist AI to Specialized Medical AI Applications and Their Challenges","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2508.19259","title":"Capabilities of GPT-5 across critical domains: Is it the next breakthrough?","created":"2025-08-16","cited_by_count":6,"area":null},{"id":"2602.14879","title":"CT-Bench: A Benchmark for Multimodal Lesion Understanding in Computed Tomography","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2512.21127","title":"A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care","created":"2025-12-24","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":"2507.07421","title":"SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2502.07186","title":"PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2604.01941","title":"Captioning Daily Activity Images in Early Childhood Education: Benchmark and Algorithm","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2607.25186","title":"CardioBench: A Real-World Data Benchmark for Evaluating Large Language Models in Clinically Authentic Cardiovascular Care Scenarios","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}