{"total":16,"rows":[{"id":"2502.15871","title":"A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare","created":"2025-02-21","cited_by_count":27,"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":"2410.01106","title":"Statistical inference on black-box generative models in the data kernel perspective space","created":"2024-10-01","cited_by_count":9,"area":null},{"id":"2504.01201","title":"Medical large language models are easily distracted","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2506.03659","title":"Trustworthy Medical Question Answering: An Evaluation-Centric Survey","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2411.03883","title":"MEG: Medical Knowledge-Augmented Large Language Models for Question Answering","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2505.19562","title":"FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2602.17316","title":"Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2604.06846","title":"MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2412.05845","title":"Are Clinical T5 Models Better for Clinical Text?","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2605.17028","title":"PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2504.03786","title":"Do \"New Snow Tablets\" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2509.10963","title":"Testing for LLM response differences: the case of a composite null consisting of semantically irrelevant query perturbations","created":"2025-09-13","cited_by_count":1,"area":null},{"id":"2605.27463","title":"When prompt perturbations break your A/B test: A valid statistical test for generative surveying","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2501.10642","title":"Iterative Tree Analysis for Medical Critics","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2510.18691","title":"Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null}],"next_cursor":null}