{"total":72,"rows":[{"id":"2501.18362","title":"MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding","created":"2025-01-30","cited_by_count":224,"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":"2506.04078","title":"LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation","created":"2025-06-04","cited_by_count":34,"area":null},{"id":"2601.02151","title":"Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting","created":"2026-01-05","cited_by_count":16,"area":null},{"id":"2508.13514","title":"ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs","created":"2025-08-19","cited_by_count":13,"area":null},{"id":"2508.02621","title":"HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research","created":"2025-08-04","cited_by_count":11,"area":null},{"id":"2505.12716","title":"Shadow-FT: Tuning Instruct Model via Training on Paired Base Model","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2506.06705","title":"DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains","created":"2025-06-07","cited_by_count":9,"area":null},{"id":"2512.11437","title":"CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare","created":"2025-12-12","cited_by_count":9,"area":null},{"id":"2501.09484","title":"Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators","created":"2025-01-16","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":"2506.22808","title":"MedEthicsQA: A Comprehensive Question Answering Benchmark for Medical Ethics Evaluation of LLMs","created":"2025-06-28","cited_by_count":8,"area":null},{"id":"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":"2505.24063","title":"TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2510.10071","title":"ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2510.13500","title":"MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2601.13178","title":"Medical Triage as Pairwise Ranking: A Benchmark for Urgency in Patient Portal Messages","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2605.10761","title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2503.17599","title":"Evaluating Clinical Competencies of Large Language Models with a General Practice Benchmark","created":"2025-03-22","cited_by_count":3,"area":null},{"id":"2505.12043","title":"MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2507.05816","title":"Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematurity","created":"2025-07-08","cited_by_count":3,"area":null},{"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":"2510.12224","title":"MedKGEval: A Knowledge Graph-Based Multi-Turn Evaluation Framework for Open-Ended Patient Interactions with Clinical LLMs","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2601.05376","title":"The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models","created":"2026-01-08","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":"2603.29373","title":"Beyond Idealized Patients: Evaluating LLMs under Challenging Patient Behaviors in Medical Consultations","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2606.04067","title":"Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2508.18687","title":"Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning","created":"2025-08-26","cited_by_count":2,"area":null},{"id":"2509.21856","title":"KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.09316","title":"A Survey of LLM Prompt Datasets: Taxonomy, Linguistic Patterns, and Practical Uses","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2602.05692","title":"MedErrBench: A Fine-Grained Multilingual Benchmark for Medical Error Detection and Correction with Clinical Expert Annotations","created":"2026-02-05","cited_by_count":2,"area":null},{"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":"2501.04073","title":"Deep Learning for Ophthalmology: The State-of-the-Art and Future Trends","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2502.01243","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2505.08508","title":"TrialMatchAI: An End-to-End AI-powered Clinical Trial Recommendation System to Streamline Patient-to-Trial Matching","created":"2025-05-13","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":"2506.03489","title":"EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2510.03160","title":"SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpus","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2511.06230","title":"Overview of CHIP 2025 Shared Task 2: Discharge Medication Recommendation for Metabolic Diseases Based on Chinese Electronic Health Records","created":"2025-11-09","cited_by_count":1,"area":null},{"id":"2603.03677","title":"MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.17356","title":"PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.14543","title":"RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.23629","title":"DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.30040","title":"Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.05004","title":"SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2608.26592","title":"Benchmarking Clinical Decision Pathway Adherence in Large Language Models","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2507.14200","title":"A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.21815","title":"HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs","created":"2025-07-29","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":"2510.18691","title":"Investigating LLM Capabilities on Long Context Comprehension for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2512.02816","title":"A benchmark dataset for evaluating Syndrome Differentiation and Treatment in large language models","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.11567","title":"Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinology","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2603.23678","title":"PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.20531","title":"Effects of Cross-lingual Evidence in Multilingual Medical Question Answering","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.17368","title":"RadGenome-Anatomy: A Large-Scale Anatomy-Labeled Chest Radiograph Dataset via Physically Grounded Volumetric Projection","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.05463","title":"PSEBench: A Controllable and Verifiable Benchmark for Evaluating LLMs in Patient Safety Event Triage","created":"2026-06-03","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":"2606.10279","title":"Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.08038","title":"A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosis","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.18999","title":"MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.27806","title":"LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2607.28788","title":"EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.01012","title":"MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.06425","title":"NTDH: Complex Reasoning for Comprehensive Affective Analysis","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.14683","title":"One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.20768","title":"Beyond Endpoint Gains: A Weight-Delta Audit of Medical Specialization","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.28599","title":"CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosis","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.30676","title":"MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.12851","title":"MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.16660","title":"Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA","created":"2026-09-15","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},{"id":"2610.15322","title":"SuperAI: Merging Capabilities Across Heterogeneous Foundation Models","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}