{"total":42,"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":"2401.06866","title":"Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data","created":"2024-01-12","cited_by_count":66,"area":null},{"id":"2406.06331","title":"MedExQA: Medical Question Answering Benchmark with Multiple Explanations","created":"2024-06-10","cited_by_count":60,"area":null},{"id":"2402.16040","title":"EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries","created":"2024-02-25","cited_by_count":35,"area":null},{"id":"2406.06573","title":"MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering","created":"2024-06-03","cited_by_count":26,"area":null},{"id":"2310.19975","title":"BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing","created":"2023-10-30","cited_by_count":25,"area":null},{"id":"2407.09429","title":"Open (Clinical) LLMs are Sensitive to Instruction Phrasings","created":"2024-07-12","cited_by_count":24,"area":null},{"id":"2403.05795","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","created":"2024-03-09","cited_by_count":22,"area":null},{"id":"2410.22446","title":"Do Large Language Models Align with Core Mental Health Counseling Competencies?","created":"2024-10-29","cited_by_count":19,"area":null},{"id":"2406.10303","title":"A Survey on Large Language Models from General Purpose to Medical Applications: Datasets, Methodologies, and Evaluations","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2405.00715","title":"Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation","created":"2024-04-25","cited_by_count":9,"area":null},{"id":"2406.09923","title":"CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2408.02600","title":"BioMamba: Domain-Adaptive Biomedical Language Models","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2403.02799","title":"DPPA: Pruning Method for Large Language Model to Model Merging","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2407.05250","title":"CLIMB: A Benchmark of Clinical Bias in Large Language Models","created":"2024-07-07","cited_by_count":7,"area":null},{"id":"2405.11255","title":"WisPerMed at \"Discharge Me!\": Advancing Text Generation in Healthcare with Large Language Models, Dynamic Expert Selection, and Priming Techniques on MIMIC-IV","created":"2024-05-18","cited_by_count":6,"area":null},{"id":"2405.16115","title":"SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology","created":"2024-05-25","cited_by_count":4,"area":null},{"id":"2407.04629","title":"Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework","created":"2024-07-05","cited_by_count":4,"area":null},{"id":"2401.09637","title":"Impact of Large Language Model Assistance on Patients Reading Clinical Notes: A Mixed-Methods Study","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2410.07951","title":"Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2601.10004","title":"SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2601.11886","title":"Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence","created":"2026-01-17","cited_by_count":3,"area":null},{"id":"2402.07645","title":"Detecting the Clinical Features of Difficult-to-Treat Depression using Synthetic Data from Large Language Models","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2410.08588","title":"ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2411.03919","title":"A Causal Framework for Precision Rehabilitation","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2411.18940","title":"Rephrasing Electronic Health Records for Pretraining Clinical Language Models","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2409.08523","title":"Eir: Thai Medical Large Language Models","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2502.17571","title":"Towards Conditioning Clinical Text Generation for User Control","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2503.02365","title":"EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2509.10882","title":"Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies","created":"2025-09-13","cited_by_count":1,"area":null},{"id":"2511.01053","title":"Building a Silver-Standard Dataset from NICE Guidelines for Clinical LLMs","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2512.16189","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2604.10316","title":"Comparative Analysis of Large Language Models in Healthcare","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2504.03713","title":"RLDBF: Enhancing LLMs Via Reinforcement Learning With DataBase FeedBack","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2507.14079","title":"DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2601.01171","title":"Almost Clinical: Linguistic properties of synthetic electronic health records","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2601.19286","title":"ReToP: Learning to Rewrite Electronic Health Records for Clinical Prediction","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.24174","title":"Task-Centric Acceleration of Small-Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.17775","title":"Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.03157","title":"ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2609.29479","title":"Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.30027","title":"Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}