{"total":21,"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":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92,"area":null},{"id":"2411.09834","title":"A Benchmark for Long-Form Medical Question Answering","created":"2024-11-14","cited_by_count":25,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2503.03194","title":"Structured Outputs Enable General-Purpose LLMs to be Medical Experts","created":"2025-03-05","cited_by_count":7,"area":null},{"id":"2512.10780","title":"Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting","created":"2025-12-11","cited_by_count":5,"area":null},{"id":"2408.10573","title":"Putting People in LLMs' Shoes: Generating Better Answers via Question Rewriter","created":"2024-08-20","cited_by_count":4,"area":null},{"id":"2505.16000","title":"Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2509.21856","title":"KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2505.10472","title":"Large Language Models for Cancer Communication: Evaluating Linguistic Quality, Safety, and Accessibility in Generative AI","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.06905","title":"MedInjection-FR: Exploring the Role of Native, Synthetic, and Translated Data in Biomedical Instruction Tuning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2505.18331","title":"PerMedCQA: Benchmarking Large Language Models on Medical Consumer Question Answering in Persian Language","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2606.19266","title":"Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.11891","title":"CANDI: Contextual Alignment for Niche Domains Question Answering","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2608.00932","title":"Gaokerena: A Small Persian Medical Language Model Family","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.12884","title":"MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.13059","title":"CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}