{"total":51,"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":"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":"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":"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":"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":"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":"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":"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":"2604.14615","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":"2607.14314","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":"2509.21530","title":"Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration","created":"2025-09-25","cited_by_count":0,"area":null},{"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":"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":"2603.00917","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":"2603.20595","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":"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":"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":"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":"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}],"next_cursor":null}