{"total":135,"rows":[{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830,"area":null},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486,"area":null},{"id":"2203.03540","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","created":"2022-02-02","cited_by_count":238,"area":null},{"id":"2104.08671","title":"When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset","created":"2021-04-18","cited_by_count":201,"area":null},{"id":"2204.13258","title":"Cross-modal Memory Networks for Radiology Report Generation","created":"2022-04-28","cited_by_count":185,"area":null},{"id":"2305.13523","title":"A Study of Generative Large Language Model for Medical Research and Healthcare","created":"2023-05-22","cited_by_count":163,"area":null},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124,"area":null},{"id":"2308.08833","title":"CMB: A Comprehensive Medical Benchmark in Chinese","created":"2023-08-17","cited_by_count":115,"area":null},{"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":"2302.08091","title":"Do We Still Need Clinical Language Models?","created":"2023-02-16","cited_by_count":98,"area":null},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2306.03030","title":"Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset","created":"2023-06-05","cited_by_count":91,"area":null},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2310.06271","title":"Towards Mitigating Hallucination in Large Language Models via Self-Reflection","created":"2023-10-10","cited_by_count":81,"area":null},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70,"area":null},{"id":"2201.11838","title":"Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences","created":"2022-01-27","cited_by_count":69,"area":null},{"id":"2308.14089","title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records","created":"2023-08-27","cited_by_count":56,"area":null},{"id":"2306.15681","title":"ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram","created":"2023-06-21","cited_by_count":54,"area":null},{"id":"2310.18652","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","created":"2023-10-28","cited_by_count":53,"area":null},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46,"area":null},{"id":"2301.07695","title":"EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2503.07459","title":"MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks","created":"2025-03-10","cited_by_count":40,"area":"lr"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2301.11847","title":"A Comparative Study of Pretrained Language Models for Long Clinical Text","created":"2023-01-27","cited_by_count":35,"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":"2406.03712","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","created":"2024-06-06","cited_by_count":34,"area":null},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2409.19487","title":"HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations","created":"2024-09-28","cited_by_count":31,"area":null},{"id":"2109.08365","title":"CodeQA: A Question Answering Dataset for Source Code Comprehension","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2204.10555","title":"KALA: Knowledge-Augmented Language Model Adaptation","created":"2022-04-22","cited_by_count":21,"area":null},{"id":"2308.03253","title":"PaniniQA: Enhancing Patient Education Through Interactive Question Answering","created":"2023-08-07","cited_by_count":21,"area":null},{"id":"2106.02524","title":"CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2310.14088","title":"MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation","created":"2023-10-21","cited_by_count":19,"area":null},{"id":"2408.02056","title":"MedSyn: LLM-based Synthetic Medical Text Generation Framework","created":"2024-08-04","cited_by_count":19,"area":null},{"id":"2404.09135","title":"Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions","created":"2024-04-14","cited_by_count":18,"area":null},{"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,"area":null},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2108.01764","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","created":"2021-08-03","cited_by_count":16,"area":null},{"id":"2201.07040","title":"Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2206.02696","title":"Learning to Ask Like a Physician","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2510.10909","title":"PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature","created":"2025-10-13","cited_by_count":15,"area":"lr"},{"id":"2209.14901","title":"DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing","created":"2022-09-29","cited_by_count":14,"area":"lr"},{"id":"2306.16931","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","created":"2023-06-29","cited_by_count":14,"area":null},{"id":"2412.04272","title":"PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables","created":"2024-12-05","cited_by_count":14,"area":"lr"},{"id":"2204.03035","title":"Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding","created":"2022-04-06","cited_by_count":13,"area":null},{"id":"2512.16822","title":"MEPIC: Memory Efficient Position Independent Caching for LLM Serving","created":"2025-12-18","cited_by_count":11,"area":"rag"},{"id":"2112.05780","title":"A Scoping Review of Publicly Available Language Tasks in Clinical Natural Language Processing","created":"2021-12-07","cited_by_count":10,"area":null},{"id":"2305.12945","title":"ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2402.12749","title":"Me LLaMA: Foundation Large Language Models for Medical Applications","created":"2024-02-20","cited_by_count":10,"area":null},{"id":"2412.11757","title":"SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2108.08074","title":"MeDiaQA: A Question Answering Dataset on Medical Dialogues","created":"2021-08-18","cited_by_count":9,"area":null},{"id":"2111.14703","title":"Question Answering for Complex Electronic Health Records Database using Unified Encoder-Decoder Architecture","created":"2021-11-14","cited_by_count":9,"area":null},{"id":"2212.03613","title":"G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks","created":"2022-12-07","cited_by_count":9,"area":null},{"id":"2309.12426","title":"Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges","created":"2023-09-21","cited_by_count":9,"area":null},{"id":"2410.03502","title":"CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios","created":"2024-10-04","cited_by_count":9,"area":null},{"id":"2502.13108","title":"Clinical QA 2.0: Multi-Task Learning for Answer Extraction and Categorization","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2503.17933","title":"Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA","created":"2025-03-23","cited_by_count":9,"area":"rag"},{"id":"2405.05938","title":"DOLOMITES: Domain-Specific Long-Form Methodical Tasks","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2109.10415","title":"What Would it Take to get Biomedical QA Systems into Practice?","created":"2021-09-21","cited_by_count":7,"area":null},{"id":"2307.10188","title":"Several categories of Large Language Models (LLMs): A Short Survey","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2310.08759","title":"Question Answering for Electronic Health Records: A Scoping Review of datasets and models","created":"2023-10-12","cited_by_count":7,"area":null},{"id":"2310.10920","title":"NuclearQA: A Human-Made Benchmark for Language Models for the Nuclear Domain","created":"2023-10-17","cited_by_count":7,"area":null},{"id":"2405.11162","title":"LG AI Research & KAIST at EHRSQL 2024: Self-Training Large Language Models with Pseudo-Labeled Unanswerable Questions for a Reliable Text-to-SQL System on EHRs","created":"2024-05-18","cited_by_count":7,"area":"synth"},{"id":"2203.10839","title":"TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processing","created":"2022-03-21","cited_by_count":6,"area":null},{"id":"2204.07469","title":"Mixture of Experts for Biomedical Question Answering","created":"2022-04-15","cited_by_count":6,"area":"moe"},{"id":"2405.07348","title":"MedConceptsQA: Open Source Medical Concepts QA Benchmark","created":"2024-05-12","cited_by_count":6,"area":null},{"id":"2408.11735","title":"Clinical Insights: A Comprehensive Review of Language Models in Medicine","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2402.07812","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","created":"2024-02-12","cited_by_count":5,"area":"lr"},{"id":"2408.08624","title":"RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions","created":"2024-08-16","cited_by_count":5,"area":null},{"id":"2505.18452","title":"MedScore: Generalizable Factuality Evaluation of Free-Form Medical Answers by Domain-adapted Claim Decomposition and Verification","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2108.00513","title":"Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes","created":"2021-08-01","cited_by_count":4,"area":null},{"id":"2203.06918","title":"Uncertainty-Aware Text-to-Program for Question Answering on Structured Electronic Health Records","created":"2022-03-14","cited_by_count":4,"area":null},{"id":"2209.01174","title":"Extend and Explain: Interpreting Very Long Language Models","created":"2022-09-02","cited_by_count":4,"area":null},{"id":"2306.04551","title":"Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning","created":"2023-06-07","cited_by_count":4,"area":"lr"},{"id":"2311.02961","title":"Adapting Pre-trained Generative Models for Extractive Question Answering","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2408.11800","title":"WeQA: A Benchmark for Retrieval Augmented Generation in Wind Energy Domain","created":"2024-08-21","cited_by_count":4,"area":"rag"},{"id":"2508.14817","title":"Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs","created":"2025-08-20","cited_by_count":4,"area":"lr"},{"id":"2509.05818","title":"Chatbot To Help Patients Understand Their Health","created":"2025-09-06","cited_by_count":4,"area":null},{"id":"2607.22566","title":"MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models","created":"2026-05-31","cited_by_count":4,"area":null},{"id":"2201.02517","title":"Development of an Extractive Clinical Question Answering Dataset with Multi-Answer and Multi-Focus Questions","created":"2022-01-07","cited_by_count":3,"area":null},{"id":"2202.13174","title":"BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task","created":"2022-02-26","cited_by_count":3,"area":null},{"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,"area":null},{"id":"2405.01588","title":"Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2502.06252","title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2508.16390","title":"A Large-Scale Benchmark for Evaluating Large Language Models on Medical Question Answering in Romanian","created":"2025-08-22","cited_by_count":3,"area":null},{"id":"2601.09876","title":"Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2112.02992","title":"Towards More Robust Natural Language Understanding","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2305.08777","title":"Question-Answering System Extracts Information on Injection Drug Use from Clinical Notes","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2310.07225","title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2402.00474","title":"SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2407.16073","title":"KaPQA: Knowledge-Augmented Product Question-Answering","created":"2024-07-22","cited_by_count":2,"area":null},{"id":"2506.10751","title":"Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering","created":"2025-06-12","cited_by_count":2,"area":"agents"},{"id":"2507.02616","title":"DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making","created":"2025-07-03","cited_by_count":2,"area":"agents"},{"id":"2507.15715","title":"From Queries to Criteria: Understanding How Astronomers Evaluate LLMs","created":"2025-07-21","cited_by_count":2,"area":null},{"id":"2510.10549","title":"ELAIPBench: A Benchmark for Expert-Level Artificial Intelligence Paper Understanding","created":"2025-10-12","cited_by_count":2,"area":null}],"next_cursor":"100"}