{"total":35,"rows":[{"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":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55,"area":null},{"id":"2204.06508","title":"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations","created":"2022-04-13","cited_by_count":41,"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":"2204.10290","title":"Learning to Revise References for Faithful Summarization","created":"2022-04-13","cited_by_count":28,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"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":"2310.11648","title":"Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model","created":"2023-10-18","cited_by_count":21,"area":null},{"id":"2410.18889","title":"Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance","created":"2024-10-24","cited_by_count":20,"area":null},{"id":"2310.08372","title":"Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment","created":"2023-10-12","cited_by_count":19,"area":null},{"id":"2402.11414","title":"Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization","created":"2024-02-18","cited_by_count":10,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2203.10133","title":"Probing Factually Grounded Content Transfer with Factual Ablation","created":"2022-03-18","cited_by_count":7,"area":null},{"id":"2212.09955","title":"BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2303.05392","title":"Automatically Summarizing Evidence from Clinical Trials: A Prototype Highlighting Current Challenges","created":"2023-03-07","cited_by_count":7,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2211.02580","title":"Evaluating and Improving Factuality in Multimodal Abstractive Summarization","created":"2022-11-04","cited_by_count":6,"area":null},{"id":"2211.12118","title":"HaRiM$^+$: Evaluating Summary Quality with Hallucination Risk","created":"2022-11-22","cited_by_count":6,"area":null},{"id":"2205.02035","title":"Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency Checking","created":"2022-05-04","cited_by_count":5,"area":null},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2211.09458","title":"Abstractive Summarization Guided by Latent Hierarchical Document Structure","created":"2022-11-17","cited_by_count":4,"area":null},{"id":"2212.01611","title":"CoP: Factual Inconsistency Detection by Controlling the Preference","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2305.13309","title":"Evaluating Factual Consistency of Texts with Semantic Role Labeling","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2210.12367","title":"Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation","created":"2022-10-22","cited_by_count":3,"area":null},{"id":"2112.13432","title":"New Methods & Metrics for LFQA tasks","created":"2021-12-26","cited_by_count":2,"area":null},{"id":"2204.11190","title":"Knowledge-aware Document Summarization: A Survey of Knowledge, Embedding Methods and Architectures","created":"2022-04-24","cited_by_count":2,"area":null},{"id":"2409.14065","title":"Temporally Consistent Factuality Probing for Large Language Models","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2301.11719","title":"The Exploration of Knowledge-Preserving Prompts for Document Summarisation","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2305.10736","title":"Counterfactual Debiasing for Generating Factually Consistent Text Summaries","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2402.06220","title":"A Unified Causal View of Instruction Tuning","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2212.09726","title":"Improving Faithfulness of Abstractive Summarization by Controlling Confounding Effect of Irrelevant Sentences","created":"2022-12-19","cited_by_count":0,"area":null},{"id":"2308.12888","title":"Inducing Causal Structure for Abstractive Text Summarization","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2504.04534","title":"An Empirical Comparison of Text Summarization: A Multi-Dimensional Evaluation of Large Language Models","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2512.13714","title":"AI-Powered Annotation Pipelines for Stabilizing Large Language Models: A Human-AI Synergy Approach","created":"2025-12-08","cited_by_count":0,"area":null}],"next_cursor":null}