{"total":30,"rows":[{"id":"2405.02559","title":"A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Review","created":"2024-05-04","cited_by_count":66,"area":null},{"id":"2303.03948","title":"A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization","created":"2023-03-07","cited_by_count":14,"area":null},{"id":"2205.02549","title":"User-Driven Research of Medical Note Generation Software","created":"2022-05-05","cited_by_count":13,"area":null},{"id":"2507.05973","title":"We Should Evaluate Real-World Impact","created":"2025-07-08","cited_by_count":12,"area":null},{"id":"2212.06008","title":"Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generators","created":"2022-12-12","cited_by_count":11,"area":null},{"id":"2305.17364","title":"An Investigation of Evaluation Metrics for Automated Medical Note Generation","created":"2023-05-27","cited_by_count":10,"area":null},{"id":"2312.13871","title":"Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2405.00715","title":"Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation","created":"2024-04-25","cited_by_count":9,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2211.09455","title":"Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation","created":"2022-11-17","cited_by_count":8,"area":null},{"id":"2305.02220","title":"WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models","created":"2023-05-03","cited_by_count":7,"area":null},{"id":"2310.05857","title":"Improving Summarization with Human Edits","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2402.15422","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","created":"2024-02-23","cited_by_count":6,"area":null},{"id":"2401.07897","title":"The Pitfalls of Defining Hallucination","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2404.13307","title":"Beyond Accuracy: Investigating Error Types in GPT-4 Responses to USMLE Questions","created":"2024-04-20","cited_by_count":5,"area":null},{"id":"2410.12845","title":"Toward Relieving Clinician Burden by Automatically Generating Progress Notes using Interim Hospital Data","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2304.08763","title":"A Survey for Biomedical Text Summarization: From Pre-trained to Large Language Models","created":"2023-04-18","cited_by_count":3,"area":null},{"id":"2311.13274","title":"Enhancing Summarization Performance through Transformer-Based Prompt Engineering in Automated Medical Reporting","created":"2023-11-22","cited_by_count":3,"area":null},{"id":"2409.18170","title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2310.17279","title":"Automatic Logical Forms improve fidelity in Table-to-Text generation","created":"2023-10-26","cited_by_count":2,"area":null},{"id":"2505.17095","title":"Are LLMs reliable? An exploration of the reliability of large language models in clinical note generation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.14774","title":"MedSyn: Enhancing Diagnostics with Human-AI Collaboration","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2311.13273","title":"Comparative Experimentation of Accuracy Metrics in Automated Medical Reporting: The Case of Otitis Consultations","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2408.06259","title":"Context-aware Visual Storytelling with Visual Prefix Tuning and Contrastive Learning","created":"2024-08-12","cited_by_count":1,"area":null},{"id":"2508.13816","title":"The illusion of a perfect metric: Why evaluating AI's words is harder than it looks","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2608.23627","title":"From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency Department","created":"2026-08-23","cited_by_count":1,"area":null},{"id":"2507.03033","title":"Preserving Privacy, Increasing Accessibility, and Reducing Cost: An On-Device Artificial Intelligence Model for Medical Transcription and Note Generation","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2510.00436","title":"Automated Evaluation can Distinguish the Good and Bad AI Responses to Patient Questions about Hospitalization","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2608.14598","title":"Position: Medical AI Neglects Real Treatment Outcomes","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2609.15794","title":"KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AI","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}