{"total":122,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830,"area":null},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638,"area":null},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384,"area":null},{"id":"2402.10373","title":"BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains","created":"2024-02-15","cited_by_count":301,"area":null},{"id":"2308.11483","title":"Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions","created":"2023-08-22","cited_by_count":263,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168,"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":"2305.18703","title":"Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey","created":"2023-05-30","cited_by_count":135,"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":"2306.10070","title":"Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health","created":"2023-06-15","cited_by_count":118,"area":null},{"id":"2304.09667","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","created":"2023-04-19","cited_by_count":117,"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":"2301.12586","title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","created":"2023-01-29","cited_by_count":93,"area":null},{"id":"2212.09292","title":"ChatGPT: The End of Online Exam Integrity?","created":"2022-12-19","cited_by_count":88,"area":null},{"id":"2303.05279","title":"Can large language models build causal graphs?","created":"2023-03-07","cited_by_count":73,"area":null},{"id":"2406.12036","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","created":"2024-06-17","cited_by_count":70,"area":null},{"id":"2307.15051","title":"Matching Patients to Clinical Trials with Large Language Models","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61,"area":null},{"id":"2302.03495","title":"Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?","created":"2023-02-03","cited_by_count":54,"area":null},{"id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2309.00237","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","created":"2023-09-01","cited_by_count":51,"area":null},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2305.06299","title":"Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)","created":"2023-05-10","cited_by_count":40,"area":null},{"id":"2306.10073","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","created":"2023-06-15","cited_by_count":39,"area":null},{"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,"area":null},{"id":"2402.08113","title":"Addressing cognitive bias in medical language models","created":"2024-02-12","cited_by_count":36,"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":"2303.08033","title":"Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code","created":"2023-03-09","cited_by_count":32,"area":null},{"id":"2306.13906","title":"Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?","created":"2023-06-24","cited_by_count":31,"area":null},{"id":"2401.08396","title":"Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine","created":"2024-01-16","cited_by_count":31,"area":null},{"id":"2304.13714","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","created":"2023-04-26","cited_by_count":30,"area":null},{"id":"2303.12961","title":"The Shaky Foundations of Clinical Foundation Models: A Survey of Large Language Models and Foundation Models for EMRs","created":"2023-03-22","cited_by_count":29,"area":null},{"id":"2403.13313","title":"Polaris: A Safety-focused LLM Constellation Architecture for Healthcare","created":"2024-03-20","cited_by_count":28,"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":"2309.00087","title":"Large language models in medicine: the potentials and pitfalls","created":"2023-08-31","cited_by_count":21,"area":null},{"id":"2409.19492","title":"MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models","created":"2024-09-29","cited_by_count":21,"area":null},{"id":"2507.18905","title":"Large language models provide unsafe answers to patient-posed medical questions","created":"2025-07-25","cited_by_count":18,"area":null},{"id":"2307.09683","title":"PubMed and Beyond: Biomedical Literature Search in the Age of Artificial Intelligence","created":"2023-07-18","cited_by_count":16,"area":null},{"id":"2310.11430","title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models","created":"2023-10-17","cited_by_count":16,"area":null},{"id":"2403.01924","title":"To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering","created":"2024-03-04","cited_by_count":15,"area":null},{"id":"2307.13693","title":"Evaluating Large Language Models for Radiology Natural Language Processing","created":"2023-07-25","cited_by_count":12,"area":null},{"id":"2312.08800","title":"Evaluating Large Language Models for Health-related Queries with Presuppositions","created":"2023-12-14","cited_by_count":12,"area":null},{"id":"2504.19467","title":"BRIDGE: Benchmarking Large Language Models for Understanding Real-world Clinical Practice Text","created":"2025-04-28","cited_by_count":12,"area":null},{"id":"2305.12723","title":"Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2309.02233","title":"Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering","created":"2023-09-05","cited_by_count":11,"area":null},{"id":"2305.10163","title":"Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries","created":"2023-05-17","cited_by_count":10,"area":null},{"id":"2311.12233","title":"Unifying Corroborative and Contributive Attributions in Large Language Models","created":"2023-11-20","cited_by_count":10,"area":null},{"id":"2306.05642","title":"Customizing General-Purpose Foundation Models for Medical Report Generation","created":"2023-06-09","cited_by_count":9,"area":null},{"id":"2406.05845","title":"MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering","created":"2024-06-09","cited_by_count":9,"area":null},{"id":"2306.07170","title":"Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning","created":"2023-06-12","cited_by_count":8,"area":null},{"id":"2309.09362","title":"Language models are susceptible to incorrect patient self-diagnosis in medical applications","created":"2023-09-17","cited_by_count":8,"area":null},{"id":"2407.12814","title":"Computational Politeness in Natural Language Processing: A Survey","created":"2024-06-28","cited_by_count":8,"area":null},{"id":"2505.22787","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2506.06091","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2403.14006","title":"On Prompt Sensitivity of ChatGPT in Affective Computing","created":"2024-03-20","cited_by_count":7,"area":null},{"id":"2403.20288","title":"Can LLMs Correct Physicians, Yet? Investigating Effective Interaction Methods in the Medical Domain","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2504.13475","title":"LLM Sensitivity Evaluation Framework for Clinical Diagnosis","created":"2025-04-18","cited_by_count":7,"area":null},{"id":"2304.07396","title":"Improving Patient Pre-screening for Clinical Trials: Assisting Physicians with Large Language Models","created":"2023-04-14","cited_by_count":6,"area":null},{"id":"2312.09785","title":"RJUA-QA: A Comprehensive QA Dataset for Urology","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2401.11389","title":"MedLM: Exploring Language Models for Medical Question Answering Systems","created":"2024-01-21","cited_by_count":6,"area":null},{"id":"2405.14766","title":"Evaluating Large Language Models for Public Health Classification and Extraction Tasks","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2411.03883","title":"MEG: Medical Knowledge-Augmented Large Language Models for Question Answering","created":"2024-11-06","cited_by_count":6,"area":null},{"id":"2404.13307","title":"Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions","created":"2024-04-20","cited_by_count":5,"area":null},{"id":"2406.06616","title":"Transforming Dental Diagnostics with Artificial Intelligence: Advanced Integration of ChatGPT and Large Language Models for Patient Care","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2412.06287","title":"PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2501.15108","title":"Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2402.03349","title":"When Geoscience Meets Generative AI and Large Language Models: Foundations, Trends, and Future Challenges","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2410.18460","title":"Beyond Multiple-Choice Accuracy: Real-World Challenges of Implementing Large Language Models in Healthcare","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2501.15022","title":"Using Large Language Models for education managements in Vietnamese with low resources","created":"2025-01-25","cited_by_count":4,"area":null},{"id":"2505.07968","title":"Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2308.14641","title":"Challenges of GPT-3-based Conversational Agents for Healthcare","created":"2023-08-28","cited_by_count":3,"area":null},{"id":"2311.17502","title":"Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2401.02985","title":"Evaluating Large Language Models on the GMAT: Implications for the Future of Business Education","created":"2024-01-02","cited_by_count":3,"area":null},{"id":"2401.07510","title":"Developing ChatGPT for Biology and Medicine: A Complete Review of Biomedical Question Answering","created":"2024-01-15","cited_by_count":3,"area":null},{"id":"2410.14147","title":"Leveraging Large Language Models for Enhancing Public Transit Services","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2411.03497","title":"Uncertainty Quantification for Clinical Outcome Predictions with (Large) Language Models","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2503.18562","title":"Self-Reported Confidence of Large Language Models in Gastroenterology: Analysis of Commercial, Open-Source, and Quantized Models","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2308.14536","title":"Spoken Language Intelligence of Large Language Models for Language Learning","created":"2023-08-28","cited_by_count":2,"area":null},{"id":"2309.10359","title":"Prompt, Condition, and Generate: Classification of Unsupported Claims with In-Context Learning","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2309.12481","title":"HANS, are you clever? Clever Hans Effect Analysis of Neural Systems","created":"2023-09-21","cited_by_count":2,"area":null},{"id":"2311.09558","title":"What if you said that differently?: How Explanation Formats Affect Human Feedback Efficacy and User Perception","created":"2023-11-16","cited_by_count":2,"area":null},{"id":"2402.14047","title":"Simple and Effective Transfer Learning for Neuro-Symbolic Integration","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2404.00484","title":"Edinburgh Clinical NLP at SemEval-2024 Task 2: Fine-tune your model unless you have access to GPT-4","created":"2024-03-30","cited_by_count":2,"area":null},{"id":"2404.11973","title":"A critical review of methods and challenges in large language models","created":"2024-04-18","cited_by_count":2,"area":null},{"id":"2405.18028","title":"Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding Large Language Models with Hints","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2406.16611","title":"Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2409.01497","title":"DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using Large Language Models","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2409.15127","title":"Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2503.07306","title":"Benchmarking Chinese Medical LLMs: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.00008","title":"A Scoping Review of Natural Language Processing in Addressing Medically Inaccurate Information: Errors, Misinformation, and Hallucination","created":"2025-04-16","cited_by_count":2,"area":null},{"id":"2308.11827","title":"Exploring the Effectiveness of GPT Models in Test-Taking: A Case Study of the Driver's License Knowledge Test","created":"2023-08-22","cited_by_count":1,"area":null}],"next_cursor":"100"}