{"total":16,"rows":[{"id":"2604.05081","title":"MedGemma 1.5 Technical Report","created":"2026-04-06","cited_by_count":45,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2502.04397","title":"Multimodal Medical Code Tokenizer","created":"2025-02-06","cited_by_count":14,"area":null},{"id":"2508.11894","title":"QuarkMed Medical Foundation Model Technical Report","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2509.24506","title":"Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings","created":"2025-09-29","cited_by_count":5,"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":"2605.15000","title":"Quantifying and Mitigating Premature Closure in Frontier LLMs","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2506.21578","title":"HealthQA-BR: A System-Wide Benchmark Reveals Critical Knowledge Gaps in Large Language Models","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2602.01714","title":"MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2606.12250","title":"Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2508.20810","title":"From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.11517","title":"PeruMedQA: Benchmarking Large Language Models (LLMs) on Peruvian Medical Exams -- Dataset Construction and Evaluation","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2605.16215","title":"Fully Open Meditron: An Auditable Pipeline for Clinical LLMs","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.04024","title":"Instruction Duplication as an Inference-Time Control Primitive","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.09684","title":"Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16301","title":"CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}