{"total":58,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211,"area":null},{"id":"2408.02442","title":"Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models","created":"2024-08-05","cited_by_count":96,"area":null},{"id":"2402.06341","title":"RareBench: Can LLMs Serve as Rare Diseases Specialists?","created":"2024-02-09","cited_by_count":45,"area":null},{"id":"2407.13301","title":"CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis","created":"2024-07-18","cited_by_count":43,"area":null},{"id":"2408.12547","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","created":"2024-08-22","cited_by_count":40,"area":null},{"id":"2305.13614","title":"LLM-empowered Chatbots for Psychiatrist and Patient Simulation: Application and Evaluation","created":"2023-05-23","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":"2304.13188","title":"TABLET: Learning From Instructions For Tabular Data","created":"2023-04-25","cited_by_count":28,"area":null},{"id":"2406.01394","title":"PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration","created":"2024-06-03","cited_by_count":28,"area":null},{"id":"2410.14204","title":"MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations","created":"2024-10-18","cited_by_count":22,"area":null},{"id":"2405.02764","title":"Assessing Adversarial Robustness of Large Language Models: An Empirical Study","created":"2024-05-04","cited_by_count":21,"area":null},{"id":"2503.17509","title":"Follow-up Question Generation For Enhanced Patient-Provider Conversations","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2510.23476","title":"Human-AI Collaborative Uncertainty Quantification","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2502.13321","title":"Adjust for Trust: Mitigating Trust-Induced Inappropriate Reliance on AI Assistance","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2210.07198","title":"Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2412.06287","title":"PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2407.07330","title":"Interpretable Differential Diagnosis with Dual-Inference Large Language Models","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2601.06636","title":"MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2312.01242","title":"DDxT: Deep Generative Transformer Models for Differential Diagnosis","created":"2023-12-02","cited_by_count":3,"area":null},{"id":"2402.01723","title":"An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarios","created":"2024-01-27","cited_by_count":3,"area":null},{"id":"2601.19773","title":"Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2605.25052","title":"Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2402.16926","title":"On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2406.10950","title":"E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2408.15827","title":"Automatic Differential Diagnosis using Transformer-Based Multi-Label Sequence Classification","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2604.07549","title":"EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2607.14385","title":"MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2505.23075","title":"Second Opinion Matters: Towards Adaptive Clinical AI via the Consensus of Expert Model Ensemble","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.06737","title":"C-PATH: Conversational Patient Assistance and Triage in Healthcare System","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2510.03700","title":"H-DDx: A Hierarchical Evaluation Framework for Differential Diagnosis","created":"2025-10-04","cited_by_count":1,"area":null},{"id":"2510.27274","title":"Traceable Drug Recommendation over Medical Knowledge Graphs","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2601.21551","title":"Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2607.20848","title":"Auditing Evidence Use in Medical LLM Diagnosis","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.25085","title":"MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2410.12868","title":"IMAS: A Comprehensive Agentic Approach to Rural Healthcare Delivery","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2506.19702","title":"LLM-Driven Medical Document Analysis: Enhancing Trustworthy Pathology and Differential Diagnosis","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2510.15970","title":"Predict Training Data Quality via Its Geometry in Metric Space","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2511.05485","title":"MIMIC-SR-ICD11: A Dataset for Narrative-Based Diagnosis","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2511.06592","title":"MedVoiceBias: A Controlled Study of Audio LLM Behavior in Clinical Decision-Making","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2512.02043","title":"Mirror, Mirror on the Wall -- Which is the Best Model of Them All?","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2601.15645","title":"Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.09130","title":"UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.01444","title":"Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.10441","title":"VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.18613","title":"Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance","created":"2026-06-17","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":"2607.28788","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":"2608.03674","title":"DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.09024","title":"ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.24521","title":"Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.27847","title":"From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis","created":"2026-08-28","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":"2609.16800","title":"Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.35627","title":"Can LLMs Value the Right Evidence? Evidence-Value Misalignment in Dynamic Medical Diagnosis","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04542","title":"Decide, Ask, or Defer: Clinical LLMs under Incomplete Evidence","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}