{"total":38,"rows":[{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"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":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"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":"2208.11646","title":"Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation","created":"2022-08-24","cited_by_count":75,"area":null},{"id":"2104.00054","title":"A Statistical Analysis of Summarization Evaluation Metrics using Resampling Methods","created":"2021-03-31","cited_by_count":72,"area":null},{"id":"2109.11503","title":"Finding a Balanced Degree of Automation for Summary Evaluation","created":"2021-09-23","cited_by_count":43,"area":null},{"id":"2406.12673","title":"Estimating Knowledge in Large Language Models Without Generating a Single Token","created":"2024-06-18","cited_by_count":40,"area":null},{"id":"2204.10216","title":"Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics","created":"2022-04-21","cited_by_count":38,"area":null},{"id":"2303.03608","title":"Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation","created":"2023-03-07","cited_by_count":24,"area":null},{"id":"2402.17630","title":"Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Tasks","created":"2024-02-27","cited_by_count":23,"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":"2105.12437","title":"The statistical advantage of automatic NLG metrics at the system level","created":"2021-05-26","cited_by_count":18,"area":null},{"id":"2208.07316","title":"MENLI: Robust Evaluation Metrics from Natural Language Inference","created":"2022-08-15","cited_by_count":18,"area":null},{"id":"2404.11184","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2211.16853","title":"Revisiting text decomposition methods for NLI-based factuality scoring of summaries","created":"2022-11-30","cited_by_count":14,"area":null},{"id":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2210.13449","title":"Controlled Text Reduction","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2412.07096","title":"QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization","created":"2024-12-10","cited_by_count":8,"area":null},{"id":"2506.19352","title":"Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation","created":"2025-06-24","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":"2403.01774","title":"WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2406.00842","title":"The Power of Summary-Source Alignments","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2305.15044","title":"Is Summary Useful or Not? An Extrinsic Human Evaluation of Text Summaries on Downstream Tasks","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2404.01701","title":"On the Role of Summary Content Units in Text Summarization Evaluation","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2406.06938","title":"Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges","created":"2024-06-11","cited_by_count":5,"area":null},{"id":"2502.06617","title":"Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2210.06576","title":"DATScore: Evaluating Translation with Data Augmented Translations","created":"2022-10-12","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","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":"2507.05965","title":"OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2105.06027","title":"Towards Human-Free Automatic Quality Evaluation of German Summarization","created":"2021-05-13","cited_by_count":0,"area":null},{"id":"2110.03567","title":"GeSERA: General-domain Summary Evaluation by Relevance Analysis","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2211.04903","title":"Novel Chapter Abstractive Summarization using Spinal Tree Aware Sub-Sentential Content Selection","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2604.07553","title":"TR-EduVSum: A Turkish-Focused Dataset and Consensus Framework for Educational Video Summarization","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.19185","title":"SCURank: Ranking Multiple Candidate Summaries with Summary Content Units for Enhanced Summarization","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":null}