{"total":44,"rows":[{"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":"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":"2604.27470","title":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","created":"2026-04-30","cited_by_count":26,"area":null},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2509.16584","title":"From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2601.06586","title":"Detecting LLM-Generated Text with Performance Guarantees","created":"2026-01-10","cited_by_count":10,"area":null},{"id":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2509.18776","title":"AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2508.11894","title":"QuarkMed Medical Foundation Model Technical Report","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2510.08009","title":"Language Models Do Not Embed Numbers Continuously","created":"2025-10-09","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":"2601.13244","title":"Do Instruction-Tuned Models Always Perform Better Than Base Models? Evidence from Math and Domain-Shifted Benchmarks","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2606.10388","title":"Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2503.03802","title":"RiskAgent: Synergizing Language Models with Validated Tools for Evidence-Based Risk Prediction","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2511.20836","title":"Structured Prompts Improve Evaluation of Language Models","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2601.23049","title":"MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2510.00038","title":"DM-Bench: Benchmarking LLMs for Personalized Decision Making in Diabetes Management","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2512.19691","title":"Scalable Stewardship of an LLM-Assisted Clinical Benchmark with Physician Oversight","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2411.05897","title":"Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators","created":"2024-11-08","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":"2510.20001","title":"Beyond MedQA: Towards Real-world Clinical Decision Making in the Era of LLMs","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2605.04468","title":"Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control","created":"2026-05-06","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":"2606.12203","title":"Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.26836","title":"The Capability Frontier: Benchmarks Miss 82% of Model Performance","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2502.11703","title":"CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2510.17764","title":"Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.27267","title":"MedCalc-Eval and MedCalc-Env: Advancing Medical Calculation Capabilities of Large Language Models","created":"2025-10-31","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":"2603.29893","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":"2607.20453","title":"A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2609.01982","title":"Benchmarking Language Models for Statistical Problem Formulation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.10728","title":"Towards a Deterministic Math Solver for Clinical Language Models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.12277","title":"Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.22262","title":"Large language models in medical time series analysis","created":"2026-09-07","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":"2609.31908","title":"Improving Medical Calculation of LLMs with Embedded Coding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33845","title":"How code helps different tasks? A decompositional lens on LLM post-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34112","title":"Unknown is not normal: separating language-model extraction from rule-based decision logic for clinical risk scores","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34780","title":"Applying Language Models in Clinical Medicine: Recent Trends and Perspectives","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01592","title":"Which LLM to pick? Online Active Model Selection for Large Language Models","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05489","title":"SkillGATE: Gate-Aware Monte Carlo Tree Search for Skill Retrieval","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.18201","title":"How Reliable Are Large Language Models for Soil Organic Carbon Assessment? An Australian Benchmark","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18529","title":"How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}