{"list":"other","total":58,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2401.00396","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","created":"2023-12-31","cited_by_count":283},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265},{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244},{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231},{"id":"2501.18362","title":"MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding","created":"2025-01-30","cited_by_count":224},{"id":"2402.09181","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","created":"2024-02-14","cited_by_count":184},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154},{"id":"1809.00732","title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records","created":"2018-09-03","cited_by_count":135},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115},{"id":"2307.02028","title":"EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models","created":"2023-07-05","cited_by_count":105},{"id":"2402.09742","title":"AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator","created":"2024-02-15","cited_by_count":101},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97},{"id":"2408.06142","title":"Med42-v2: A Suite of Clinical LLMs","created":"2024-08-12","cited_by_count":90},{"id":"1908.01839","title":"Text-to-SQL Generation for Question Answering on Electronic Medical Records","created":"2019-07-28","cited_by_count":77},{"id":"2406.03949","title":"UltraMedical: Building Specialized Generalists in Biomedicine","created":"2024-06-06","cited_by_count":67},{"id":"2406.06331","title":"MedExQA: Medical Question Answering Benchmark with Multiple Explanations","created":"2024-06-10","cited_by_count":60},{"id":"2506.22405","title":"Sequential Diagnosis with Language Models","created":"2025-06-27","cited_by_count":60},{"id":"2308.14089","title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records","created":"2023-08-27","cited_by_count":56},{"id":"2408.12547","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","created":"2024-08-22","cited_by_count":40},{"id":"2403.03640","title":"Apollo: A Lightweight Multilingual Medical LLM towards Democratizing Medical AI to 6B People","created":"2024-03-06","cited_by_count":38},{"id":"2402.16040","title":"EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries","created":"2024-02-25","cited_by_count":35},{"id":"2503.04176","title":"TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records","created":"2025-03-06","cited_by_count":34},{"id":"2506.04078","title":"LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation","created":"2025-06-04","cited_by_count":34},{"id":"2401.14490","title":"LongHealth: A Question Answering Benchmark with Long Clinical Documents","created":"2024-01-25","cited_by_count":33},{"id":"2503.04691","title":"Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases","created":"2025-03-06","cited_by_count":29},{"id":"2506.09513","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","created":"2025-06-11","cited_by_count":27},{"id":"2505.22919","title":"ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room","created":"2025-05-28","cited_by_count":22},{"id":"2507.07988","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","created":"2025-07-10","cited_by_count":22},{"id":"2010.09394","title":"Knowledge Graph-based Question Answering with Electronic Health Records","created":"2020-10-19","cited_by_count":19},{"id":"2510.25628","title":"EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis","created":"2025-10-29","cited_by_count":18},{"id":"2205.01290","title":"DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queries","created":"2022-05-03","cited_by_count":17},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17},{"id":"2402.11217","title":"A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models","created":"2024-02-17","cited_by_count":16},{"id":"2406.14326","title":"medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs","created":"2024-06-20","cited_by_count":16},{"id":"2405.07500","title":"PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking","created":"2024-05-13","cited_by_count":15},{"id":"2510.04284","title":"Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning","created":"2025-10-05","cited_by_count":14},{"id":"2405.00716","title":"Large Language Models in the Clinic: A Comprehensive Benchmark","created":"2024-04-25","cited_by_count":13},{"id":"2406.15019","title":"MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens","created":"2024-06-21","cited_by_count":13},{"id":"2503.07667","title":"CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models","created":"2025-03-09","cited_by_count":13},{"id":"2507.02773","title":"KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs","created":"2025-07-03","cited_by_count":12},{"id":"2511.09895","title":"Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation","created":"2025-11-13","cited_by_count":8},{"id":"2406.10061","title":"TACCO: Task-guided Co-clustering of Clinical Concepts and Patient Visits for Disease Subtyping based on EHR Data","created":"2024-06-14","cited_by_count":7},{"id":"2405.07348","title":"MedConceptsQA: Open Source Medical Concepts QA Benchmark","created":"2024-05-12","cited_by_count":6},{"id":"2503.06204","title":"CUPCase: Clinically Uncommon Patient Cases and Diagnoses Dataset","created":"2025-03-08","cited_by_count":6},{"id":"2406.02919","title":"MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge","created":"2024-06-05","cited_by_count":5},{"id":"2108.00513","title":"Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes","created":"2021-08-01","cited_by_count":4},{"id":"2502.03298","title":"MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters","created":"2025-02-05","cited_by_count":4},{"id":"2303.07069","title":"Generating multiple-choice questions for medical question answering with distractors and cue-masking","created":"2023-03-13","cited_by_count":3},{"id":"2510.20001","title":"Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs","created":"2025-10-22","cited_by_count":1},{"id":"2603.13673","title":"LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes","created":"2026-03-14","cited_by_count":1}],"next_cursor":null}