{"total":19,"rows":[{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327,"area":null},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142,"area":null},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96,"area":null},{"id":"2105.00816","title":"What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization","created":"2021-04-12","cited_by_count":35,"area":null},{"id":"2101.06561","title":"GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation","created":"2021-01-17","cited_by_count":20,"area":null},{"id":"2109.09195","title":"Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries","created":"2021-09-19","cited_by_count":15,"area":null},{"id":"2305.14341","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2212.10397","title":"Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization","created":"2022-12-20","cited_by_count":10,"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":"2211.09455","title":"Consultation Checklists: Standardising the Human Evaluation of Medical Note Generation","created":"2022-11-17","cited_by_count":8,"area":null},{"id":"2101.11298","title":"How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2108.01879","title":"Summary Explorer: Visualizing the State of the Art in Text Summarization","created":"2021-08-04","cited_by_count":4,"area":null},{"id":"2607.27739","title":"Measuring Alignment With Reader Highlights Net of Position and Length","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2308.02270","title":"Redundancy Aware Multi-Reference Based Gainwise Evaluation of Extractive Summarization","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2509.21713","title":"Developing Strategies to Increase Capacity in AI Education","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2201.05294","title":"Multi-Narrative Semantic Overlap Task: Evaluation and Benchmark","created":"2022-01-14","cited_by_count":0,"area":null},{"id":"2311.09458","title":"Lexical Repetitions Lead to Rote Learning: Unveiling the Impact of Lexical Overlap in Train and Test Reference Summaries","created":"2023-11-15","cited_by_count":0,"area":null}],"next_cursor":null}