{"total":194,"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":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331,"area":"rag"},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316,"area":"lr"},{"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":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231,"area":"agents"},{"id":"2405.02957","title":"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents","created":"2024-05-05","cited_by_count":218,"area":"agents"},{"id":"2307.00716","title":"JourneyDB: A Benchmark for Generative Image Understanding","created":"2023-07-03","cited_by_count":205,"area":"mllm"},{"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":"2303.01229","title":"Almanac: Retrieval-Augmented Language Models for Clinical Medicine","created":"2023-03-01","cited_by_count":123,"area":"rag"},{"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":"2311.17371","title":"Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs","created":"2023-11-29","cited_by_count":114,"area":"agents"},{"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":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97,"area":"rag"},{"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":"2305.18395","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":64,"area":"lr"},{"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":"2408.00727","title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","created":"2024-08-01","cited_by_count":54,"area":"rag"},{"id":"2303.17071","title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","created":"2023-03-30","cited_by_count":52,"area":"agents"},{"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":"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":"2503.22678","title":"Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions","created":"2025-03-28","cited_by_count":40,"area":"agents"},{"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":"2502.11418","title":"TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents","created":"2025-02-17","cited_by_count":37,"area":"agents"},{"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":"2403.04890","title":"Few shot chain-of-thought driven reasoning to prompt LLMs for open ended medical question answering","created":"2024-03-07","cited_by_count":31,"area":"lr"},{"id":"2404.14777","title":"ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning","created":"2024-04-23","cited_by_count":31,"area":"lr"},{"id":"2502.04381","title":"Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning","created":"2025-02-05","cited_by_count":31,"area":"lr"},{"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":"2509.01790","title":"Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs","created":"2025-09-01","cited_by_count":30,"area":"lr"},{"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":"2402.07023","title":"Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations","created":"2024-02-10","cited_by_count":27,"area":"mllm"},{"id":"2506.09513","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","created":"2025-06-11","cited_by_count":27,"area":"lr"},{"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":"2301.11596","title":"ThoughtSource: A central hub for large language model reasoning data","created":"2023-01-27","cited_by_count":23,"area":"lr"},{"id":"2401.16107","title":"Beyond Direct Diagnosis: LLM-based Multi-Specialist Agent Consultation for Automatic Diagnosis","created":"2024-01-29","cited_by_count":23,"area":"agents"},{"id":"2506.04405","title":"MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science","created":"2025-06-04","cited_by_count":23,"area":"lr"},{"id":"2507.07988","title":"Automating Expert-Level Medical Reasoning Evaluation of Large Language Models","created":"2025-07-10","cited_by_count":22,"area":"lr"},{"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":"2410.04660","title":"KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA","created":"2024-10-07","cited_by_count":20,"area":"agents"},{"id":"2403.06609","title":"Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds","created":"2024-03-11","cited_by_count":19,"area":"lr"},{"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":"2304.02496","title":"Evaluation of ChatGPT Family of Models for Biomedical Reasoning and Classification","created":"2023-04-05","cited_by_count":17,"area":"lr"},{"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":"2502.18274","title":"Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support","created":"2025-02-25","cited_by_count":16,"area":"lr"},{"id":"2505.07889","title":"BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science","created":"2025-05-11","cited_by_count":16,"area":"lr"},{"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":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2501.02460","title":"Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications","created":"2025-01-05","cited_by_count":13,"area":"rag"},{"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":"2410.05361","title":"RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction","created":"2024-10-07","cited_by_count":10,"area":"mllm"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2510.07176","title":"Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions","created":"2025-10-08","cited_by_count":10,"area":"agents"},{"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":"2509.21933","title":"Why Chain of Thought Fails in Clinical Text Understanding","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"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":"2507.18115","title":"Agentic AI framework for End-to-End Medical Data Inference","created":"2025-07-24","cited_by_count":8,"area":"agents"},{"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}],"next_cursor":"100"}