{"total":136,"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":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722,"area":null},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422,"area":null},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361,"area":null},{"id":"2112.08542","title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","created":"2021-12-16","cited_by_count":236,"area":null},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169,"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":"2405.01724","title":"Large Language Models are Inconsistent and Biased Evaluators","created":"2024-05-02","cited_by_count":153,"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":"2304.02554","title":"Human-like Summarization Evaluation with ChatGPT","created":"2023-04-05","cited_by_count":126,"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":"2311.09766","title":"LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores","created":"2023-11-16","cited_by_count":90,"area":null},{"id":"2407.00908","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","created":"2024-07-01","cited_by_count":83,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"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":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"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":"2311.09184","title":"Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization","created":"2023-11-15","cited_by_count":69,"area":null},{"id":"2210.12563","title":"On the Limitations of Reference-Free Evaluations of Generated Text","created":"2022-10-22","cited_by_count":52,"area":null},{"id":"2104.06387","title":"ExplainaBoard: An Explainable Leaderboard for NLP","created":"2021-04-13","cited_by_count":50,"area":null},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48,"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":"2310.10632","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","created":"2023-10-16","cited_by_count":43,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38,"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":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2201.11176","title":"DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence","created":"2022-01-26","cited_by_count":36,"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":"2112.01589","title":"InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation","created":"2021-12-02","cited_by_count":33,"area":null},{"id":"2209.03549","title":"Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization","created":"2022-09-08","cited_by_count":32,"area":null},{"id":"2405.13769","title":"Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation","created":"2024-05-22","cited_by_count":32,"area":null},{"id":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2309.07382","title":"Less is More for Long Document Summary Evaluation by LLMs","created":"2023-09-14","cited_by_count":28,"area":null},{"id":"2204.09890","title":"Spurious Correlations in Reference-Free Evaluation of Text Generation","created":"2022-04-21","cited_by_count":26,"area":null},{"id":"2210.16732","title":"How Far are We from Robust Long Abstractive Summarization?","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2107.14691","title":"EmailSum: Abstractive Email Thread Summarization","created":"2021-07-30","cited_by_count":24,"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":"2105.03311","title":"Translation Quality Assessment: A Brief Survey on Manual and Automatic Methods","created":"2021-05-05","cited_by_count":23,"area":null},{"id":"2507.01001","title":"SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks","created":"2025-07-01","cited_by_count":20,"area":null},{"id":"2205.09641","title":"SNaC: Coherence Error Detection for Narrative Summarization","created":"2022-05-19","cited_by_count":19,"area":null},{"id":"2210.04705","title":"Readability Controllable Biomedical Document Summarization","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2208.01030","title":"SMART: Sentences as Basic Units for Text Evaluation","created":"2022-08-01","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":"2212.10179","title":"Toward Human-Like Evaluation for Natural Language Generation with Error Analysis","created":"2022-12-20","cited_by_count":18,"area":null},{"id":"2405.15604","title":"Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challenges","created":"2024-05-24","cited_by_count":18,"area":null},{"id":"2103.12711","title":"A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions","created":"2021-03-23","cited_by_count":17,"area":null},{"id":"2106.11388","title":"How well do you know your summarization datasets?","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2206.02696","title":"Learning to Ask Like a Physician","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2305.08566","title":"NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist","created":"2023-05-15","cited_by_count":16,"area":null},{"id":"2305.14702","title":"DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2402.11683","title":"One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation","created":"2024-02-18","cited_by_count":16,"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":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2212.01669","title":"A Survey on Medical Document Summarization","created":"2022-12-03","cited_by_count":14,"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":"2305.10284","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","created":"2023-05-17","cited_by_count":14,"area":null},{"id":"2310.18122","title":"OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization","created":"2023-10-27","cited_by_count":13,"area":null},{"id":"2310.14103","title":"Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications","created":"2023-10-21","cited_by_count":11,"area":null},{"id":"2311.04694","title":"Evaluating Generative Ad Hoc Information Retrieval","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11,"area":null},{"id":"2109.06853","title":"Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension","created":"2021-09-14","cited_by_count":10,"area":null},{"id":"2208.14585","title":"The Glass Ceiling of Automatic Evaluation in Natural Language Generation","created":"2022-08-31","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":"2412.09269","title":"Towards Understanding the Robustness of LLM-based Evaluations under Perturbations","created":"2024-12-12","cited_by_count":10,"area":null},{"id":"2208.04083","title":"Template-based Abstractive Microblog Opinion Summarisation","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2208.04163","title":"Abstractive Meeting Summarization: A Survey","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2312.01032","title":"Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions using Large Language Models","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2108.09484","title":"cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSE","created":"2021-08-21","cited_by_count":8,"area":null},{"id":"2306.12916","title":"Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2412.00868","title":"Quantifying perturbation impacts for large language models","created":"2024-12-01","cited_by_count":8,"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":"2506.07947","title":"Statistical Hypothesis Testing for Auditing Robustness in Language Models","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2507.05123","title":"An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2601.08654","title":"From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges","created":"2026-01-13","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":"2410.12893","title":"MIRROR: A Novel Approach for the Automated Evaluation of Open-Ended Question Generation","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2104.05156","title":"Estimation of Summary-to-Text Inconsistency by Mismatched Embeddings","created":"2021-04-12","cited_by_count":5,"area":null},{"id":"2401.09150","title":"Bridging Research and Readers: A Multi-Modal Automated Academic Papers Interpretation System","created":"2024-01-17","cited_by_count":5,"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":"2501.00097","title":"CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions","created":"2024-12-30","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":"2208.13265","title":"Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods","created":"2022-08-28","cited_by_count":4,"area":null},{"id":"2310.17217","title":"Beyond MLE: Convex Learning for Text Generation","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2406.07967","title":"Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2410.16834","title":"Analyzing and Evaluating Correlation Measures in NLG Meta-Evaluation","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2604.17197","title":"Learning to Control Summaries with Score Ranking","created":"2026-04-19","cited_by_count":4,"area":null},{"id":"2108.10763","title":"ComSum: Commit Messages Summarization and Meaning Preservation","created":"2021-08-23","cited_by_count":3,"area":null},{"id":"2206.06383","title":"An Exploration of Post-Editing Effectiveness in Text Summarization","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2209.07417","title":"Examining Large Pre-Trained Language Models for Machine Translation: What You Don't Know About It","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2210.08859","title":"Social Biases in Automatic Evaluation Metrics for NLG","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2210.14606","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2407.00453","title":"PerSEval: Assessing Personalization in Text Summarizers","created":"2024-06-29","cited_by_count":3,"area":null},{"id":"2501.13100","title":"A Rate-Distortion Framework for Summarization","created":"2025-01-22","cited_by_count":3,"area":null},{"id":"2509.17829","title":"Towards Adaptive Context Management for Intelligent Conversational Question Answering","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2201.09282","title":"WIDAR -- Weighted Input Document Augmented ROUGE","created":"2022-01-23","cited_by_count":2,"area":null}],"next_cursor":"100"}