{"total":76,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288,"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":"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":"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":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98,"area":null},{"id":"2211.08412","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization","created":"2022-11-15","cited_by_count":92,"area":null},{"id":"2104.14839","title":"The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey","created":"2021-04-30","cited_by_count":79,"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":"2104.07606","title":"Planning with Learned Entity Prompts for Abstractive Summarization","created":"2021-04-15","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":"2312.17249","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","created":"2023-12-28","cited_by_count":67,"area":"mechinterp"},{"id":"2107.03175","title":"A Survey on Dialogue Summarization: Recent Advances and New Frontiers","created":"2021-07-07","cited_by_count":51,"area":null},{"id":"2108.13684","title":"Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization","created":"2021-08-31","cited_by_count":51,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2207.00397","title":"Conditional Generation with a Question-Answering Blueprint","created":"2022-07-01","cited_by_count":44,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"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":"2105.11921","title":"Focus Attention: Promoting Faithfulness and Diversity in Summarization","created":"2021-05-25","cited_by_count":30,"area":null},{"id":"2203.15108","title":"A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation","created":"2022-03-28","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":"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":"2203.00130","title":"Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2405.13179","title":"RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts","created":"2024-05-21","cited_by_count":23,"area":"rag"},{"id":"2204.13761","title":"Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization","created":"2022-04-28","cited_by_count":20,"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":"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":"2403.03823","title":"A Modular Approach for Multimodal Summarization of TV Shows","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2408.13704","title":"DHP Benchmark: Are LLMs Good NLG Evaluators?","created":"2024-08-25","cited_by_count":12,"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":"2411.16638","title":"Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2204.13921","title":"QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance","created":"2022-04-29","cited_by_count":9,"area":null},{"id":"2305.00034","title":"Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation","created":"2023-04-28","cited_by_count":9,"area":null},{"id":"2407.06501","title":"STORYSUMM: Evaluating Faithfulness in Story Summarization","created":"2024-07-09","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":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2305.16626","title":"Evaluation of Question Generation Needs More References","created":"2023-05-26","cited_by_count":8,"area":null},{"id":"2104.00336","title":"Mitigating Media Bias through Neutral Article Generation","created":"2021-04-01","cited_by_count":7,"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":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2406.14709","title":"Factual Dialogue Summarization via Learning from Large Language Models","created":"2024-06-20","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":"2307.00963","title":"Challenges in Domain-Specific Abstractive Summarization and How to Overcome them","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2502.13674","title":"SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2405.19285","title":"MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection","created":"2024-05-29","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":"2307.02570","title":"Named Entity Inclusion in Abstractive Text Summarization","created":"2023-07-05","cited_by_count":3,"area":null},{"id":"2411.08715","title":"Retrieval Augmented Recipe Generation","created":"2024-11-13","cited_by_count":3,"area":"mllm"},{"id":"2211.08464","title":"ED-FAITH: Evaluating Dialogue Summarization on Faithfulness","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2409.19507","title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2508.16267","title":"From Confidence to Collapse in LLM Factual Robustness","created":"2025-08-22","cited_by_count":2,"area":null},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2511.07689","title":"Stress Testing Factual Consistency Metrics for Long-Document Summarization","created":"2025-11-10","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":"2112.11638","title":"Consistency and Coherence from Points of Contextual Similarity","created":"2021-12-22","cited_by_count":1,"area":null},{"id":"2303.14222","title":"Lay Text Summarisation Using Natural Language Processing: A Narrative Literature Review","created":"2023-03-24","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":"2210.00667","title":"Probing of Quantitative Values in Abstractive Summarization Models","created":"2022-10-03","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":"2211.04364","title":"NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?","created":"2022-11-08","cited_by_count":0,"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":"2305.02104","title":"Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2305.14991","title":"MuLER: Detailed and Scalable Reference-based Evaluation","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2401.07190","title":"Inroads to a Structured Data Natural Language Bijection and the role of LLM annotation","created":"2024-01-14","cited_by_count":0,"area":null},{"id":"2405.00289","title":"Adversarial Attacks and Defense for Conversation Entailment Task","created":"2024-05-01","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},{"id":"2609.15561","title":"Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer Perturbation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.22603","title":"Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2610.02877","title":"Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}