{"total":90,"rows":[{"id":"2410.13085","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","created":"2024-10-16","cited_by_count":85,"area":"mllm"},{"id":"2504.00869","title":"m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models","created":"2025-04-01","cited_by_count":46,"area":"lr"},{"id":"2502.14302","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models","created":"2025-02-20","cited_by_count":34,"area":null},{"id":"2411.06469","title":"ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?","created":"2024-11-10","cited_by_count":32,"area":null},{"id":"2409.07314","title":"MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical Applications","created":"2024-09-11","cited_by_count":25,"area":"safety"},{"id":"2501.12051","title":"MedS$^3$: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision","created":"2025-01-21","cited_by_count":24,"area":"lr"},{"id":"2504.07887","title":"Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge","created":"2025-04-10","cited_by_count":23,"area":"safety"},{"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":"2412.06141","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2502.06666","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2505.10717","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","created":"2025-05-15","cited_by_count":20,"area":"alignment"},{"id":"2410.19155","title":"Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use","created":"2024-10-24","cited_by_count":17,"area":null},{"id":"2510.04284","title":"Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning","created":"2025-10-05","cited_by_count":14,"area":"agents"},{"id":"2410.02026","title":"Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics","created":"2024-10-02","cited_by_count":11,"area":"agents"},{"id":"2502.03945","title":"Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond","created":"2025-02-06","cited_by_count":11,"area":null},{"id":"2411.08870","title":"The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models","created":"2024-11-13","cited_by_count":9,"area":"mllm"},{"id":"2502.05478","title":"OntoTune: Ontology-Driven Self-training for Aligning Large Language Models","created":"2025-02-08","cited_by_count":8,"area":"alignment"},{"id":"2506.22808","title":"MedEthicsQA: A Comprehensive Question Answering Benchmark for Medical Ethics Evaluation of LLMs","created":"2025-06-28","cited_by_count":8,"area":null},{"id":"2507.05517","title":"Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical Applications","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2508.00743","title":"Multi-step retrieval and reasoning improves radiology question answering with large language models","created":"2025-08-01","cited_by_count":7,"area":"lr"},{"id":"2511.08206","title":"EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks","created":"2025-11-11","cited_by_count":6,"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":"2511.10067","title":"Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning","created":"2025-11-13","cited_by_count":4,"area":null},{"id":"2601.03578","title":"PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics","created":"2026-01-07","cited_by_count":4,"area":"alignment"},{"id":"2604.04325","title":"Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2604.08559","title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2502.07963","title":"Caught in the Web of Words: Do LLMs Fall for Spin in Medical Literature?","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2502.08954","title":"Medicine on the Edge: Comparative Performance Analysis of On-Device LLMs for Clinical Reasoning","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2506.08349","title":"Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2506.11166","title":"Test-Time-Scaling for Zero-Shot Diagnosis with Visual-Language Reasoning","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2509.04534","title":"Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2509.13879","title":"Combining Evidence and Reasoning for Biomedical Fact-Checking","created":"2025-09-17","cited_by_count":3,"area":"lr"},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.18556","title":"Building Trust in Clinical LLMs: Bias Analysis and Dataset Transparency","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2512.10195","title":"AutoMedic: An Automated Evaluation Framework for Clinical Conversational Agents with Medical Dataset Grounding","created":"2025-12-11","cited_by_count":3,"area":"agents"},{"id":"2602.01714","title":"MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2501.09825","title":"Bridging Language Barriers in Healthcare: A Study on Arabic LLMs","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2506.00134","title":"Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2507.07248","title":"MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2508.01970","title":"Improving Hospital Risk Prediction with Knowledge-Augmented Multimodal EHR Modeling","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2509.11078","title":"Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data","created":"2025-09-14","cited_by_count":2,"area":"agents"},{"id":"2602.05374","title":"Cross-Lingual Empirical Evaluation of Large Language Models for Arabic Medical Tasks","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.06271","title":"Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering","created":"2026-03-06","cited_by_count":2,"area":"lr"},{"id":"2605.28025","title":"MIRA: A Bilingual Benchmark for Medical Information Response Audit","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2605.29146","title":"SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2605.30637","title":"EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2503.02365","title":"EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2505.15024","title":"Diagnosing our datasets: How does my language model learn clinical information?","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2510.17532","title":"OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction","created":"2025-10-20","cited_by_count":1,"area":"lr"},{"id":"2601.06519","title":"MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation","created":"2026-01-10","cited_by_count":1,"area":"rag"},{"id":"2603.01124","title":"ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models","created":"2026-03-01","cited_by_count":1,"area":"lr"},{"id":"2606.12699","title":"LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.29034","title":"The strength of clinical evidence is recoverable from language model representations but not from their stated grades","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.13036","title":"Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.20848","title":"Auditing Evidence Use in Medical LLM Diagnosis","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2607.27512","title":"Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.06539","title":"Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2409.05732","title":"Towards Democratizing Multilingual Large Language Models For Medicine Through A Two-Stage Instruction Fine-tuning Approach","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2504.17360","title":"PatientDx: Merging Large Language Models for Protecting Data-Privacy in Healthcare","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.08734","title":"NurValues: Real-World Nursing Values Evaluation for Large Language Models in Clinical Context","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2507.18143","title":"HIVMedQA: Benchmarking large language models for HIV medical decision support","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2507.21159","title":"MAC: Masked Agent Collaboration Boosts Large Language Model Medical Decision-Making","created":"2025-07-25","cited_by_count":0,"area":"agents"},{"id":"2508.07221","title":"LLM-based Agents for Automated Confounder Discovery and Subgroup Analysis in Causal Inference","created":"2025-08-10","cited_by_count":0,"area":"agents"},{"id":"2508.13754","title":"Expertise-aware Multi-LLM Recruitment and Collaboration for Medical Decision-Making","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2509.19375","title":"Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.07173","title":"NurseLLM: The First Specialized Language Model for Nursing","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2510.18468","title":"IMB: An Italian Medical Benchmark for Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2510.26683","title":"Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2512.05576","title":"CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning","created":"2025-12-05","cited_by_count":0,"area":"lr"},{"id":"2601.13690","title":"Dr. Assistant: Enhancing Clinical Diagnostic Inquiry via Structured Diagnostic Reasoning Data and Reinforcement Learning","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2603.05129","title":"MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.09416","title":"Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.10494","title":"Coverage-Controlled Preference Mining from Noisy Claim Verification for Evidence-Grounded Generation","created":"2026-03-11","cited_by_count":0,"area":"alignment"},{"id":"2603.12458","title":"Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs","created":"2026-03-12","cited_by_count":0,"area":"lr"},{"id":"2604.05435","title":"CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.04882","title":"FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection","created":"2026-05-06","cited_by_count":0,"area":"mllm"},{"id":"2605.05963","title":"TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.12313","title":"Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.15589","title":"MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models","created":"2026-05-15","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":"2605.27860","title":"C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.03399","title":"Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.08071","title":"SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.24901","title":"LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.24838","title":"MedJudgeRAG: Option-Wise Evidence Judgment with Dynamic Knowledge Graphs for Medical MCQA","created":"2026-07-24","cited_by_count":0,"area":"rag"},{"id":"2608.00207","title":"Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.14598","title":"Position: Medical AI Neglects Real Treatment Outcomes","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2609.22216","title":"The Effect of Quantization on Clinical Benchmarks: Accuracy and Safety Across Model Families","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.26913","title":"COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.19762","title":"PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}