{"total":91,"rows":[{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407,"area":null},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290,"area":null},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"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":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184,"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":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138,"area":null},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132,"area":null},{"id":"2109.09209","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","created":"2021-09-19","cited_by_count":120,"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":"2109.06379","title":"Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation","created":"2021-09-14","cited_by_count":60,"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":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2207.00397","title":"Conditional Generation with a Question-Answering Blueprint","created":"2022-07-01","cited_by_count":44,"area":null},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2108.13134","title":"Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation","created":"2021-08-30","cited_by_count":37,"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":"2112.04139","title":"Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand","created":"2021-12-08","cited_by_count":32,"area":null},{"id":"2301.12307","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","created":"2023-01-28","cited_by_count":30,"area":null},{"id":"2204.10290","title":"Learning to Revise References for Faithful Summarization","created":"2022-04-13","cited_by_count":28,"area":null},{"id":"2105.05361","title":"The Summary Loop: Learning to Write Abstractive Summaries Without Examples","created":"2021-05-11","cited_by_count":27,"area":null},{"id":"2102.08585","title":"Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View","created":"2021-02-17","cited_by_count":24,"area":null},{"id":"2310.13189","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","created":"2023-10-19","cited_by_count":23,"area":null},{"id":"2104.07555","title":"Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation","created":"2021-04-15","cited_by_count":21,"area":null},{"id":"2106.13945","title":"A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance and Self-referenced Redundancy","created":"2021-06-26","cited_by_count":21,"area":null},{"id":"2205.08221","title":"Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning","created":"2022-05-17","cited_by_count":18,"area":null},{"id":"2311.09212","title":"Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey","created":"2023-11-15","cited_by_count":18,"area":null},{"id":"2411.05375","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2104.07560","title":"Rethinking Automatic Evaluation in Sentence Simplification","created":"2021-04-15","cited_by_count":17,"area":null},{"id":"2108.03405","title":"Controllable Summarization with Constrained Markov Decision Process","created":"2021-08-07","cited_by_count":17,"area":null},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2108.02859","title":"Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization","created":"2021-08-05","cited_by_count":16,"area":null},{"id":"2108.12560","title":"QACE: Asking Questions to Evaluate an Image Caption","created":"2021-08-28","cited_by_count":15,"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":"2210.06748","title":"Shortcomings of Question Answering Based Factuality Frameworks for Error Localization","created":"2022-10-13","cited_by_count":15,"area":null},{"id":"2410.02381","title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2103.10918","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","created":"2021-03-19","cited_by_count":13,"area":null},{"id":"2310.18122","title":"OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization","created":"2023-10-27","cited_by_count":13,"area":null},{"id":"2110.07166","title":"CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization","created":"2021-10-14","cited_by_count":11,"area":null},{"id":"2305.16548","title":"Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2404.11124","title":"What's under the hood: Investigating Automatic Metrics on Meeting Summarization","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2501.12011","title":"Reference-free Evaluation Metrics for Text Generation: A Survey","created":"2025-01-21","cited_by_count":9,"area":null},{"id":"2201.12320","title":"Generative Cooperative Networks for Natural Language Generation","created":"2022-01-28","cited_by_count":8,"area":null},{"id":"2306.05119","title":"Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework","created":"2023-06-08","cited_by_count":7,"area":null},{"id":"2211.12118","title":"HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk","created":"2022-11-22","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":"2104.05156","title":"Estimation of Summary-to-Text Inconsistency by Mismatched Embeddings","created":"2021-04-12","cited_by_count":5,"area":null},{"id":"2111.07935","title":"Incorporating Question Answering-Based Signals into Abstractive Summarization via Salient Span Selection","created":"2021-11-15","cited_by_count":5,"area":null},{"id":"2309.15016","title":"Question-Answering Approach to Evaluating Legal Summaries","created":"2023-09-26","cited_by_count":5,"area":null},{"id":"2405.19094","title":"Faithful Chart Summarization with ChaTS-Pi","created":"2024-05-29","cited_by_count":5,"area":null},{"id":"2410.10867","title":"Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2412.15189","title":"Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2205.14748","title":"Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition","created":"2022-05-29","cited_by_count":4,"area":null},{"id":"2301.03403","title":"A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2306.10452","title":"MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2205.12394","title":"MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification","created":"2022-05-24","cited_by_count":3,"area":null},{"id":"2212.01956","title":"Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2305.16895","title":"UMSE: Unified Multi-scenario Summarization Evaluation","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2306.03866","title":"Correction of Errors in Preference Ratings from Automated Metrics for Text Generation","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2403.17640","title":"REFeREE: A REference-FREE Model-Based Metric for Text Simplification","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2408.07277","title":"Speech vs. Transcript: Does It Matter for Human Annotators in Speech Summarization?","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2501.09092","title":"SteLLA: A Structured Grading System Using LLMs with RAG","created":"2025-01-15","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},{"id":"2204.10206","title":"Benchmarking Answer Verification Methods for Question Answering-Based Summarization Evaluation Metrics","created":"2022-04-21","cited_by_count":2,"area":null},{"id":"2204.13848","title":"Repro: An Open-Source Library for Improving the Reproducibility and Usability of Publicly Available Research Code","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2309.10066","title":"Automatic Personalized Impression Generation for PET Reports Using Large Language Models","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2403.04787","title":"Ever-Evolving Memory by Blending and Refining the Past","created":"2024-03-03","cited_by_count":2,"area":null},{"id":"2404.13246","title":"ISQA: Informative Factuality Feedback for Scientific Summarization","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2406.01131","title":"Favi-Score: A Measure for Favoritism in Automated Preference Ratings for Generative AI Evaluation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2503.17039","title":"Evaluating the Evaluator: Summarization Metrics and LLM-Judges beyond English","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2506.14335","title":"References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2102.05924","title":"Toward Improving Coherence and Diversity of Slogan Generation","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2107.10935","title":"DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines","created":"2021-07-22","cited_by_count":1,"area":null},{"id":"2112.11638","title":"Consistency and Coherence from Points of Contextual Similarity","created":"2021-12-22","cited_by_count":1,"area":null},{"id":"2209.12714","title":"Text Summarization with Oracle Expectation","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2311.18041","title":"Zero-shot Conversational Summarization Evaluations with small Large Language Models","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2401.04522","title":"LUNA: A Framework for Language Understanding and Naturalness Assessment","created":"2024-01-09","cited_by_count":1,"area":null},{"id":"2604.25130","title":"LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization","created":"2026-04-28","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":"2204.04869","title":"Evaluation of Automatic Text Summarization using Synthetic Facts","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2210.02804","title":"Just ClozE! A Novel Framework for Evaluating the Factual Consistency Faster in Abstractive Summarization","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2411.07521","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2504.05420","title":"PreSumm: Predicting Summarization Performance Without Summarizing","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2511.06183","title":"BookAsSumQA: An Evaluation Framework for Aspect-Based Book Summarization via Question Answering","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2603.12165","title":"QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.25665","title":"LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2608.14457","title":"Information Satisfaction: A Reader-Centered Axis for Summarization Evaluation","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}