{"total":103,"rows":[{"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":"2307.00589","title":"MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval","created":"2023-07-02","cited_by_count":185,"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":"2502.08177","title":"SycEval: Evaluating LLM Sycophancy","created":"2025-02-12","cited_by_count":108,"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":"2408.06142","title":"Med42-v2: A Suite of Clinical LLMs","created":"2024-08-12","cited_by_count":90,"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":"2404.14779","title":"Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches","created":"2024-04-23","cited_by_count":52,"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":"2305.01526","title":"Huatuo-26M, a Large-scale Chinese Medical QA Dataset","created":"2023-05-02","cited_by_count":46,"area":null},{"id":"2102.04110","title":"Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration","created":"2021-02-08","cited_by_count":44,"area":null},{"id":"2107.02975","title":"Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review","created":"2021-07-07","cited_by_count":35,"area":null},{"id":"2402.14873","title":"Technical Report on the Pangram AI-Generated Text Classifier","created":"2024-02-21","cited_by_count":34,"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":"2306.05480","title":"Artificial General Intelligence for Medical Imaging Analysis","created":"2023-06-08","cited_by_count":32,"area":null},{"id":"2203.00130","title":"Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2109.03079","title":"GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation","created":"2021-09-07","cited_by_count":20,"area":null},{"id":"2402.14259","title":"Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond","created":"2024-02-22","cited_by_count":18,"area":null},{"id":"2502.14427","title":"Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models","created":"2025-02-20","cited_by_count":18,"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":"2405.06545","title":"Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval","created":"2024-05-10","cited_by_count":16,"area":null},{"id":"2505.20045","title":"Efficient Hallucination Detection for LLMs Using Uncertainty-Aware Attention Heads","created":"2025-05-26","cited_by_count":16,"area":null},{"id":"2111.07267","title":"Understanding Jargon: Combining Extraction and Generation for Definition Modeling","created":"2021-11-14","cited_by_count":15,"area":null},{"id":"2510.04849","title":"When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA","created":"2025-10-06","cited_by_count":14,"area":null},{"id":"2306.14457","title":"Fauno: The Italian Large Language Model that will leave you senza parole!","created":"2023-06-26","cited_by_count":13,"area":null},{"id":"2603.19223","title":"F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World","created":"2026-03-19","cited_by_count":12,"area":null},{"id":"2106.00219","title":"Question-aware Transformer Models for Consumer Health Question Summarization","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","cited_by_count":11,"area":null},{"id":"2509.10970","title":"The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models","created":"2025-09-13","cited_by_count":11,"area":null},{"id":"2408.10692","title":"Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models","created":"2024-08-20","cited_by_count":9,"area":null},{"id":"2409.14988","title":"Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs","created":"2024-09-23","cited_by_count":8,"area":null},{"id":"2501.04974","title":"SensorQA: A Question Answering Benchmark for Daily-Life Monitoring","created":"2025-01-09","cited_by_count":8,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2502.15418","title":"MHQA: A Diverse, Knowledge Intensive Mental Health Question Answering Challenge for Language Models","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2507.03279","title":"Conformal Information Pursuit for Interactively Guiding Large Language Models","created":"2025-07-04","cited_by_count":7,"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":"2402.12170","title":"Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction","created":"2024-02-16","cited_by_count":6,"area":null},{"id":"2410.23111","title":"Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2501.00208","title":"An Empirical Evaluation of Large Language Models on Consumer Health Questions","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2209.12617","title":"Evaluation of Question Answering Systems: Complexity of judging a natural language","created":"2022-09-10","cited_by_count":5,"area":null},{"id":"2304.07437","title":"Medical Question Summarization with Entity-driven Contrastive Learning","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2410.20763","title":"Evaluating LLMs for Targeted Concept Simplification for Domain-Specific Texts","created":"2024-10-28","cited_by_count":5,"area":null},{"id":"2412.21052","title":"Towards Effective Discrimination Testing for Generative AI","created":"2024-12-30","cited_by_count":5,"area":null},{"id":"2411.18831","title":"Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark","created":"2024-11-28","cited_by_count":4,"area":null},{"id":"2112.13946","title":"The University of Texas at Dallas HLTRI's Participation in EPIC-QA: Searching for Entailed Questions Revealing Novel Answer Nuggets","created":"2021-12-28","cited_by_count":3,"area":null},{"id":"2209.15301","title":"Medical Question Understanding and Answering with Knowledge Grounding and Semantic Self-Supervision","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2311.16588","title":"Ascle: A Python Natural Language Processing Toolkit for Medical Text Generation","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2402.01700","title":"Question answering systems for health professionals at the point of care -- a systematic review","created":"2024-01-24","cited_by_count":3,"area":null},{"id":"2406.03699","title":"M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2108.00775","title":"Self-supervised Answer Retrieval on Clinical Notes","created":"2021-08-02","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":"2405.20821","title":"Pursuing Overall Welfare in Federated Learning through Sequential Decision Making","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2407.16434","title":"Enhancing LLM's Cognition via Structurization","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2408.17377","title":"NDP: Next Distribution Prediction as a More Broad Target","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2504.05563","title":"Do Data Valuations Make Good Data Prices?","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2506.11105","title":"Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation","created":"2025-06-07","cited_by_count":2,"area":null},{"id":"2507.19407","title":"Towards Domain Specification of Embedding Models in Medicine","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2508.20416","title":"DentalBench: Benchmarking and Advancing LLMs Capability for Bilingual Dentistry Understanding","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2605.29473","title":"Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.04127","title":"When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.02520","title":"MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2110.09321","title":"COVIDRead: A Large-scale Question Answering Dataset on COVID-19","created":"2021-10-05","cited_by_count":1,"area":null},{"id":"2111.14083","title":"A Grounded Well-being Conversational Agent with Multiple Interaction Modes: Preliminary Results","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2308.03043","title":"3D-EX : A Unified Dataset of Definitions and Dictionary Examples","created":"2023-08-06","cited_by_count":1,"area":null},{"id":"2410.03521","title":"Building a Chinese Medical Dialogue System: Integrating Large-scale Corpora and Novel Models","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2410.06566","title":"Detecting Bias and Enhancing Diagnostic Accuracy in Large Language Models for Healthcare","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2412.07021","title":"Sequential Compression Layers for Efficient Federated Learning in Foundational Models","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2502.20988","title":"Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2508.02945","title":"LLM-based IR-system for Bank Supervisors","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.00806","title":"CaresAI at BioCreative IX Track 1 -- LLM for Biomedical QA","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2509.16442","title":"Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2511.02246","title":"Demo: Statistically Significant Results On Biases and Errors of LLMs Do Not Guarantee Generalizable Results","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2604.11662","title":"A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.01301","title":"Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2609.32867","title":"Are You Sure You're Sure? Two Confounds in a Sycophancy Benchmark","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2310.10571","title":"Emerging Challenges in Personalized Medicine: Assessing Demographic Effects on Biomedical Question Answering Systems","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2311.10697","title":"PEFT-MedAware: Large Language Model for Medical Awareness","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2401.03181","title":"A Joint-Reasoning based Disease Q&A System","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2407.21053","title":"Knowledge Models for Cancer Clinical Practice Guidelines : Construction, Management and Usage in Question Answering","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2410.11141","title":"Can Structured Data Reduce Epistemic Uncertainty?","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2501.10642","title":"Iterative Tree Analysis for Medical Critics","created":"2025-01-18","cited_by_count":0,"area":null},{"id":"2504.17780","title":"Replay to Remember: Retaining Domain Knowledge in Streaming Language Models","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2510.18691","title":"Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.21006","title":"TrackList: Tracing Back Query Linguistic Diversity for Head and Tail Knowledge in Open Large Language Models","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2601.11573","title":"An Empirical Analysis of Fine-Tuning Large Language Models on Bioinformatics Literature: PRSGPT and BioStarsGPT","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2601.22645","title":"Beyond Medical Chatbots: Meddollina and the Rise of Continuous Clinical Intelligence","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.04731","title":"Modular Expert Merging for Biomedical Retrieval","created":"2026-02-04","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":"2603.01690","title":"Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.19249","title":"Spelling Correction in Healthcare Query-Answer Systems: Methods, Retrieval Impact, and Empirical Evaluation","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.10535","title":"Evaluating Small Open LLMs for Medical Question Answering: A Practical Framework","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.20791","title":"Can \"AI\" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.21807","title":"When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answering","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25988","title":"What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.28329","title":"$M^3 QuestionIng$: Multi-modal Multi-span Medical Question Answering","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.21097","title":"When Trust Meets Truth: Trust-Truth Separability in LLM-as-Judge","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":"100"}