{"total":60,"rows":[{"id":"2503.07459","title":"MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks","created":"2025-03-10","cited_by_count":40,"area":"lr"},{"id":"2502.15871","title":"A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare","created":"2025-02-21","cited_by_count":27,"area":null},{"id":"2411.09834","title":"A Benchmark for Long-Form Medical Question Answering","created":"2024-11-14","cited_by_count":25,"area":null},{"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":"2506.08584","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering","created":"2025-06-10","cited_by_count":21,"area":null},{"id":"2505.17312","title":"AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models","created":"2025-05-22","cited_by_count":17,"area":"lr"},{"id":"2504.13861","title":"3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark","created":"2025-03-26","cited_by_count":16,"area":"mllm"},{"id":"2504.14657","title":"A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMs","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2505.22240","title":"BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2506.06091","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2603.07539","title":"MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs","created":"2026-03-08","cited_by_count":8,"area":"lr"},{"id":"2506.03659","title":"Trustworthy Medical Question Answering: An Evaluation-Centric Survey","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2502.17132","title":"Applications of Large Models in Medicine","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2603.22096","title":"GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning","created":"2026-03-23","cited_by_count":6,"area":"lr"},{"id":"2503.07041","title":"TCM-3CEval: A Triaxial Benchmark for Assessing Responses from Large Language Models in Traditional Chinese Medicine","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2506.03490","title":"Beyond Memorization: A Rigorous Evaluation Framework for Medical Knowledge Editing","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2509.17628","title":"MSCoRe: A Benchmark for Multi-Stage Collaborative Reasoning in LLM Agents","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2510.11985","title":"CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2601.09876","title":"Patient-Similarity Cohort Reasoning in Clinical Text-to-SQL","created":"2026-01-14","cited_by_count":3,"area":null},{"id":"2502.20245","title":"From Retrieval to Generation: Comparing Different Approaches","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2503.04972","title":"Evaluating Answer Reranking Strategies in Time-sensitive Question Answering","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2505.18283","title":"TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2505.21503","title":"Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making","created":"2025-05-27","cited_by_count":2,"area":"agents"},{"id":"2506.04051","title":"High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2508.07353","title":"Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2601.17284","title":"Mind the Ambiguity: Aleatoric Uncertainty Quantification in LLMs for Safe Medical Question Answering","created":"2026-01-24","cited_by_count":2,"area":null},{"id":"2605.01417","title":"Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.12361","title":"MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2605.13045","title":"Large Language Models Lack Temporal Awareness of Medical Knowledge","created":"2026-05-13","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":"2504.16116","title":"DMind Benchmark: Toward a Holistic Assessment of LLM Capabilities across the Web3 Domain","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2505.16102","title":"Continually Self-Improving Language Models for Bariatric Surgery Question--Answering","created":"2025-05-22","cited_by_count":1,"area":"synth"},{"id":"2506.11017","title":"TeleEval-OS: Performance evaluations of large language models for operations scheduling","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2509.07135","title":"MedBench-IT: A Comprehensive Benchmark for Evaluating Large Language Models on Italian Medical Entrance Examinations","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.17444","title":"Filling in the Clinical Gaps in Benchmark: Case for HealthBench for the Japanese medical system","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2509.23058","title":"Risk Profiling and Modulation for LLMs","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2601.06193","title":"MLB: A Scenario-Driven Benchmark for Evaluating Large Language Models in Clinical Applications","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2605.17436","title":"Medical Context Distorts Decisions in Clinical Vision Language Models","created":"2026-05-17","cited_by_count":1,"area":"mllm"},{"id":"2609.00296","title":"Toward Workflow-Aware Benchmarking for Healthcare NLP Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2409.19177","title":"Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria","created":"2024-09-27","cited_by_count":0,"area":"alignment"},{"id":"2504.00748","title":"IHC-LLMiner: Automated extraction of tumour immunohistochemical profiles from PubMed abstracts using large language models","created":"2025-04-01","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":"2505.18331","title":"PerMedCQA: Benchmarking Large Language Models on Medical Consumer Question Answering in Persian Language","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2511.01360","title":"Safer in Translation? Presupposition Robustness in Indic Languages","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.09986","title":"Quantifying Hallucinations in Language Language Models on Medical Textbooks","created":"2026-02-12","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":"2604.20263","title":"AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.23356","title":"VeriLLMed: Interactive Visual Debugging of Medical Large Language Models with Knowledge Graphs","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.09661","title":"MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies","created":"2026-05-10","cited_by_count":0,"area":"rag"},{"id":"2605.18111","title":"How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.25566","title":"Uncertainty Reasoning with Large Language Models for Explainable Disease Diagnosis","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.04262","title":"Can I Take Another Dose? Evaluating LLM Decision-Making Under Temporal Uncertainty in OTC Dosing QA","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":"2606.16583","title":"Uncertainty Is Not a Safety Net for Clinical VQA, but Can It Anticipate Model Failure?","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2609.09684","title":"Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.16301","title":"CLEAR: Cross-Source Evidence Adjudication for Large Language Models in Medicine","created":"2026-09-14","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":"2610.13059","title":"CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}