{"total":62,"rows":[{"id":"2404.15155","title":"MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making","created":"2024-04-22","cited_by_count":163,"area":null},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"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":"2411.15640","title":"AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset","created":"2024-11-23","cited_by_count":26,"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":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2504.11373","title":"Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions","created":"2025-04-15","cited_by_count":15,"area":null},{"id":"2505.03427","title":"MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks","created":"2025-05-06","cited_by_count":15,"area":null},{"id":"2506.14028","title":"MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2404.04067","title":"Does Biomedical Training Lead to Better Medical Performance?","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"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":"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":"2503.22746","title":"Susceptibility of Large Language Models to User-Driven Factors in Medical Queries","created":"2025-03-26","cited_by_count":6,"area":null},{"id":"2605.23932","title":"When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure","created":"2026-04-23","cited_by_count":6,"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":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2508.11894","title":"QuarkMed Medical Foundation Model Technical Report","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2410.16574","title":"How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2501.17860","title":"Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2505.21657","title":"Explaining Large Language Models with gSMILE","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2512.10206","title":"CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment","created":"2025-12-11","cited_by_count":4,"area":null},{"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":"2509.15403","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering","created":"2025-09-18","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":"2601.19773","title":"Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis","created":"2026-01-27","cited_by_count":3,"area":null},{"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":"2603.18773","title":"Automatic Configuration of LLM Post-Training Pipelines","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.28819","title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2410.13259","title":"From Babbling to Fluency: Evaluating the Evolution of Language Models in Terms of Human Language Acquisition","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2605.01011","title":"CLEAR: Revealing How Noise and Ambiguity Degrade Reliability in LLMs for Medicine","created":"2026-05-01","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":"2506.00095","title":"ClinBench-HPB: A Clinical Benchmark for Evaluating LLMs in Hepato-Pancreato-Biliary Diseases","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.00612","title":"Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation","created":"2025-05-31","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":"2606.07853","title":"Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2410.12868","title":"IMAS: A Comprehensive Agentic Approach to Rural Healthcare Delivery","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2508.09719","title":"Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.12217","title":"HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment","created":"2025-10-14","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":"2512.21515","title":"Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.15674","title":"What Patients Really Ask: Exploring the Effect of False Assumptions in Patient Information Seeking","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.11460","title":"ADRD-Bench: A Preliminary LLM Benchmark for Alzheimer's Disease and Related Dementias","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.11394","title":"Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.29893","title":"Perfecting Human-AI Interaction at Clinical Scale. Turning Production Signals into Safer, More Human Conversations","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.06262","title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.06650","title":"A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.14306","title":"EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.09492","title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.09883","title":"TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.11189","title":"A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design","created":"2026-06-09","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":"2608.29453","title":"AI Can Be Easily Persuaded in Clinical Decision Making","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.04242","title":"Training-Free Speech-Centric Omni Understanding with Frozen VLMs","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.12884","title":"MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.22161","title":"Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.24799","title":"When Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs","created":"2026-09-21","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":"2609.28697","title":"LabFactory: Building and Evaluating Executable AI Labs","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.02856","title":"Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05966","title":"HuatuoGPT-3: RL-Only Domain Adaptation from Base Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}