mlsanityData to 7 Oct 2026

Factual Error Correction for Abstractive Summarization Models

arXiv 2010.08712 ↗First posted 17 Oct 2020cs.CL cs.AIcited by 108

Not on the map. Why?

Abstract (arXiv)

Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge. We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries. The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries. These transformations are inspired by an error analysis of state-of-the-art summarization model outputs. Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset. We also find that transferring from artificial error correction to downstream settings is still very challenging.

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 24; 2023: 38; 2024: 18; 2025: 7; 2026: 3.

108 papers.

Sort:

By area:

  1. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  2. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  3. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  4. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  5. 2023GPTScore: Evaluate as You Desirecited by 357
  6. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  7. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  8. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  9. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  10. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  11. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 154
  12. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
38 more
  1. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 128
  2. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 123
  3. 2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
  4. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 103
  5. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  6. 2021The Factual Inconsistency Problem in Abstractive Text Summarization: A Surveycited by 79
  7. 2021Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selectioncited by 75
  8. 2024Aligning LLM Agents by Learning Latent Preference from User Editscited by 66
  9. 2023PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptionscited by 53
  10. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  11. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  12. 2022FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarizationcited by 49
  13. 2023Detecting and Mitigating Hallucinations in Multilingual Summarisationcited by 48
  14. 2023Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioningcited by 47
  15. 2021Keep it Simple: Unsupervised Simplification of Multi-Paragraph Textcited by 45
  16. 2022FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representationscited by 41
  17. 2022Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infillingcited by 38
  18. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  19. 2024Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinationscited by 38
  20. 2023Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinationscited by 34
  21. 2022Learning to Revise References for Faithful Summarizationcited by 28
  22. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  23. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  24. 2023Zero-shot Faithful Factual Error Correctioncited by 26
  25. 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responsescited by 25
  26. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20
  27. 2024KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Modelscited by 20
  28. 2021TODSum: Task-Oriented Dialogue Summarization with State Trackingcited by 19
  29. 2023"Why is this misleading?": Detecting News Headline Hallucinations with Explanationscited by 17
  30. 2023Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarizationcited by 16
  31. 2021Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summariescited by 15
  32. 2022Shortcomings of Question Answering Based Factuality Frameworks for Error Localizationcited by 15
  33. 2021A Survey of Natural Language Generationcited by 13
  34. 2022Improving Factual Consistency in Summarization with Compression-Based Post-Editingcited by 13
  35. 2022Analyzing and Evaluating Faithfulness in Dialogue Summarizationcited by 12
  36. 2021CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarizationcited by 11
  37. 2023Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogscited by 11
  38. 2023SWING: Balancing Coverage and Faithfulness for Dialogue Summarizationcited by 10

50 most cited of 108 All 108 (JSON)