{"total":93,"rows":[{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2505.14963","title":"MedBrowseComp: Benchmarking Medical Deep Research and Computer Use","created":"2025-05-20","cited_by_count":30,"area":null},{"id":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29,"area":"agents"},{"id":"2602.06570","title":"Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making","created":"2026-02-06","cited_by_count":11,"area":null},{"id":"2509.04492","title":"Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate","created":"2025-09-01","cited_by_count":10,"area":null},{"id":"2601.15160","title":"Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2511.06738","title":"Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights","created":"2025-11-10","cited_by_count":6,"area":"lr"},{"id":"2506.12263","title":"A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2509.08604","title":"Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2603.24579","title":"MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination","created":"2026-03-25","cited_by_count":5,"area":"rag"},{"id":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"id":"2504.18080","title":"Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization","created":"2025-04-25","cited_by_count":4,"area":"lr"},{"id":"2509.18316","title":"Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning","created":"2025-09-22","cited_by_count":4,"area":"lr"},{"id":"2509.23379","title":"CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding","created":"2025-09-27","cited_by_count":4,"area":"mllm"},{"id":"2510.05126","title":"Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2510.13926","title":"BioMedSearch: A Multi-Source Biomedical Retrieval Framework Based on LLMs","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2512.09403","title":"Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMs","created":"2025-12-10","cited_by_count":4,"area":"alignment"},{"id":"2512.13510","title":"MedCEG: Reinforcing Verifiable Medical Reasoning with Critical Evidence Graph","created":"2025-12-15","cited_by_count":4,"area":"lr"},{"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":"2505.22661","title":"GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2511.12991","title":"Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2511.16544","title":"WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2510.00508","title":"Copy-Paste to Mitigate Large Language Model Hallucinations","created":"2025-10-01","cited_by_count":2,"area":"rag"},{"id":"2510.21228","title":"DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services","created":"2025-10-24","cited_by_count":2,"area":"agents"},{"id":"2510.24476","title":"Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2512.15808","title":"Foundation Models in Biomedical Imaging: Turning Hype into Reality","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2601.21003","title":"Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2603.03541","title":"RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering","created":"2026-03-03","cited_by_count":2,"area":"rag"},{"id":"2603.05884","title":"Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2604.11258","title":"Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate","created":"2026-04-13","cited_by_count":2,"area":"mllm"},{"id":"2605.10002","title":"Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2606.14697","title":"ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning","created":"2026-06-12","cited_by_count":2,"area":"lr"},{"id":"2607.11175","title":"The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy","created":"2026-07-13","cited_by_count":2,"area":"mllm"},{"id":"2507.04943","title":"ReLoop: \"Seeing Twice and Thinking Backwards\" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding","created":"2025-07-07","cited_by_count":1,"area":"lr"},{"id":"2507.07421","title":"SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2510.17476","title":"Zoom In Disparities in Healthcare LLM Q&A","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2511.02246","title":"Demo: Statistically Significant Results On Biases and Errors of LLMs Do Not Guarantee Generalizable Results","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.16189","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2601.15511","title":"AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.01343","title":"PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.14147","title":"An Alternative Trajectory for Generative AI","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2604.09482","title":"Process Reward Agents for Steering Knowledge-Intensive Reasoning","created":"2026-04-10","cited_by_count":1,"area":"rag"},{"id":"2604.14615","title":"An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.22534","title":"FeatEHR-LLM: Leveraging Large Language Models for Feature Engineering in Electronic Health Records","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.17435","title":"BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.28112","title":"A Wolf in Sheep's Clothing: Targeted Routing Hijacking in Federated RAG","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.01301","title":"Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.08982","title":"Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.07761","title":"Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2607.14314","title":"NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2505.17345","title":"The Case for Repeatable, Open, and Expert-Grounded Hallucination Benchmarks in Large Language Models","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.00205","title":"Holistic Artificial Intelligence in Medicine; improved performance and explainability","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2508.07022","title":"MultiMedEdit: A Scenario-Aware Benchmark for Evaluating Knowledge Editing in Medical VQA","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2509.10538","title":"DualAlign: Generating Clinically Grounded Synthetic Data","created":"2025-09-05","cited_by_count":0,"area":"synth"},{"id":"2509.21530","title":"Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.26153","title":"A Field Guide to Deploying AI Agents in Clinical Practice","created":"2025-09-30","cited_by_count":0,"area":"agents"},{"id":"2510.01236","title":"GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2510.01612","title":"RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering","created":"2025-10-02","cited_by_count":0,"area":"rag"},{"id":"2512.20633","title":"Enhancing Lung Cancer Treatment Outcome Prediction through Semantic Feature Engineering Using Large Language Models","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.09734","title":"From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis","created":"2025-12-31","cited_by_count":0,"area":"synth"},{"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":"2602.20040","title":"AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization","created":"2026-02-23","cited_by_count":0,"area":"agents"},{"id":"2603.00917","title":"Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2603.13236","title":"Human Attribution of Causality to AI Across Agency, Misuse, and Misalignment","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.14271","title":"Toward Clinically Ready Foundation Models in Medical Image Analysis: Adaptation Mechanisms and Deployment Trade-offs","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.20309","title":"BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs","created":"2026-03-19","cited_by_count":0,"area":"rag"},{"id":"2603.20595","title":"Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AI","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2604.06028","title":"A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models","created":"2026-04-07","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":"2605.00468","title":"ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.10025","title":"Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.19220","title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.20591","title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25020","title":"Privacy-Preserving Local Language Models for Longitudinal Data Retrieval in Chronic Dermatologic Disease: Implementation in Pemphigus Patients","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.27595","title":"Hallucination Behavior in Multimodal LLMs Across Agricultural Image Interpretation and Generation Tasks","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2606.15893","title":"BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.24155","title":"MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.29247","title":"SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Robotics","created":"2026-06-28","cited_by_count":0,"area":"vla"},{"id":"2607.03870","title":"Evaluating LLM Uncertainty in Long-Form Generation Using Deterministic Ground Truth","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.09076","title":"Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2608.03817","title":"UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.07651","title":"An Agentic AI Framework Overcomes Fundamental Limitations of Large Language Models for Glaucoma Detection from Fundus Photography","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.10725","title":"Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.14631","title":"Accuracy and Reliability of Large Language Models in Cosmetic Chemistry and Skin Health: A Benchmarking Study","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.26154","title":"Evaluating AI Generated Summaries for Cancer Patients","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2608.26587","title":"Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2608.31128","title":"DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.07194","title":"EmoMed: An Emotionally-Aware Agent for Multimodal Medical Support with Real-Time Information Retrieval","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.08364","title":"SentryLine: Evidence-Grounded Question Answering over Evolving Documents in Oncology Care","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.22206","title":"Dissecting Training-Free Uncertainty Estimation in Multimodal Large Language Models","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2610.06695","title":"MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks","created":"2026-10-05","cited_by_count":0,"area":"mllm"},{"id":"2610.16440","title":"ARMED: Adaptive Retrieval-Augmented Medication Recommendation","created":"2026-10-12","cited_by_count":0,"area":"rag"}],"next_cursor":null}