{"list":"other","total":54,"rows":[{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231},{"id":"2004.03329","title":"MedDialog: Two Large-scale Medical Dialogue Datasets","created":"2020-04-07","cited_by_count":161},{"id":"2406.00922","title":"MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning","created":"2024-06-03","cited_by_count":154},{"id":"2406.19226","title":"Simulating Classroom Education with LLM-Empowered Agents","created":"2024-06-27","cited_by_count":127},{"id":"2305.14902","title":"M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection","created":"2023-05-24","cited_by_count":121},{"id":"2306.02022","title":"ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation","created":"2023-06-03","cited_by_count":118},{"id":"2106.09449","title":"DocNLI: A Large-scale Dataset for Document-level Natural Language Inference","created":"2021-06-17","cited_by_count":75},{"id":"2407.00870","title":"Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles","created":"2024-07-01","cited_by_count":73},{"id":"2310.15959","title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","created":"2023-10-24","cited_by_count":48},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41},{"id":"2406.03712","title":"A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions","created":"2024-06-06","cited_by_count":34},{"id":"2505.17818","title":"PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions","created":"2025-05-23","cited_by_count":32},{"id":"2204.00333","title":"PriMock57: A Dataset Of Primary Care Mock Consultations","created":"2022-04-01","cited_by_count":31},{"id":"2401.06774","title":"Two Directions for Clinical Data Generation with Large Language Models: Data-to-Label and Label-to-Data","created":"2023-12-09","cited_by_count":26},{"id":"2407.00116","title":"Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges","created":"2024-06-27","cited_by_count":24},{"id":"2405.13003","title":"A Survey on Recent Advances in Conversational Data Generation","created":"2024-05-12","cited_by_count":23},{"id":"2412.11716","title":"LLMs Can Simulate Standardized Patients via Agent Coevolution","created":"2024-12-16","cited_by_count":22},{"id":"2409.16603","title":"Overview of the First Shared Task on Clinical Text Generation: RRG24 and \"Discharge Me!\"","created":"2024-09-25","cited_by_count":20},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18},{"id":"2408.06285","title":"Synthetic Patient-Physician Dialogue Generation from Clinical Notes Using LLM","created":"2024-08-12","cited_by_count":15},{"id":"2306.16931","title":"UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?","created":"2023-06-29","cited_by_count":14},{"id":"2402.00179","title":"De-identification is not enough: a comparison between de-identified and synthetic clinical notes","created":"2024-01-31","cited_by_count":14},{"id":"2410.01555","title":"ACE: A LLM-based Negotiation Coaching System","created":"2024-10-02","cited_by_count":13},{"id":"2411.17672","title":"Synthetic Data Generation with LLM for Improved Depression Prediction","created":"2024-11-26","cited_by_count":13},{"id":"2402.13919","title":"SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","created":"2024-02-21","cited_by_count":12},{"id":"2505.22450","title":"Position: All Current Generative Fidelity and Diversity Metrics are Flawed","created":"2025-05-28","cited_by_count":12},{"id":"2411.12274","title":"A Review on Generative AI Models for Synthetic Medical Text, Time Series, and Longitudinal Data","created":"2024-11-19","cited_by_count":10},{"id":"2509.07188","title":"DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge","created":"2025-09-08","cited_by_count":7},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6},{"id":"2508.20452","title":"Evaluating Differentially Private Generation of Domain-Specific Text","created":"2025-08-28","cited_by_count":5},{"id":"2507.06715","title":"CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs","created":"2025-07-09","cited_by_count":4},{"id":"2507.18451","title":"Generation of Synthetic Clinical Text: A Systematic Review","created":"2025-07-24","cited_by_count":4},{"id":"2311.07418","title":"Speech-based Slot Filling using Large Language Models","created":"2023-11-13","cited_by_count":3},{"id":"2406.06056","title":"Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text","created":"2024-06-10","cited_by_count":3},{"id":"2506.16594","title":"A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives","created":"2025-06-19","cited_by_count":3},{"id":"2508.19163","title":"MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation","created":"2025-08-26","cited_by_count":3},{"id":"2509.05006","title":"Do Large Language Models Need Intent? Revisiting Response Generation Strategies for Service Assistant","created":"2025-09-05","cited_by_count":2},{"id":"2509.05617","title":"From Joy to Fear: A Benchmark of Emotion Estimation in Pop Song Lyrics","created":"2025-09-06","cited_by_count":2},{"id":"2605.06142","title":"IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences","created":"2026-05-07","cited_by_count":2},{"id":"2605.26560","title":"Reliable Extraction of Clinical Follow-Up Instructions: A Hybrid Neural-Symbolic Pipeline","created":"2026-05-26","cited_by_count":2},{"id":"2606.03650","title":"CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks","created":"2026-06-02","cited_by_count":2},{"id":"2007.03596","title":"An Emergency Medical Services Clinical Audit System driven by Named Entity Recognition from Deep Learning","created":"2020-07-07","cited_by_count":1},{"id":"2505.03025","title":"A Typology of Synthetic Datasets for Dialogue Processing in Clinical Contexts","created":"2025-05-05","cited_by_count":1},{"id":"2509.04810","title":"Code Review Without Borders: Evaluating Synthetic vs. Real Data for Review Recommendation","created":"2025-09-05","cited_by_count":1},{"id":"2509.08304","title":"Explainable Semantic Text Relations: A Question-Answering Framework for Comparing Document Content","created":"2025-09-10","cited_by_count":1},{"id":"2509.11802","title":"When Curiosity Signals Danger: Predicting Health Crises Through Online Medication Inquiries","created":"2025-09-15","cited_by_count":1},{"id":"2509.11803","title":"From Fuzzy Speech to Medical Insight: Benchmarking LLMs on Noisy Patient Narratives","created":"2025-09-15","cited_by_count":1},{"id":"2603.22459","title":"LLM-guided headline rewriting for clickability enhancement without clickbait","created":"2026-03-23","cited_by_count":1},{"id":"2604.27014","title":"Fidelity, Diversity, and Privacy: A Multi-Dimensional LLM Evaluation for Clinical Data Augmentation","created":"2026-04-29","cited_by_count":1},{"id":"2605.25502","title":"A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis","created":"2026-05-25","cited_by_count":1},{"id":"2605.25601","title":"Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models","created":"2026-05-25","cited_by_count":1},{"id":"2606.05983","title":"Framing, Judging, Steering: An Assessable Competency Model for Teach-ing Students to Reason With Generative AI","created":"2026-06-04","cited_by_count":1}],"next_cursor":null}