# Improving Factual Consistency in Summarization with Compression-Based Post-Editing

arXiv: https://arxiv.org/abs/2211.06196 · HTML: https://mlsanity.com/paper/2211.06196/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 39 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 29 of 29)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Bottom-Up Abstractive Summarization](https://mlsanity.com/paper/1808.10792/) (2018)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [Entity-level Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/2102.09130/) (2021)
- [Factual Error Correction for Abstractive Summarization Models](https://mlsanity.com/paper/2010.08712/) (2020)
- [Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection](https://mlsanity.com/paper/2104.09061/) (2021)
- [Improved Natural Language Generation via Loss Truncation](https://mlsanity.com/paper/2004.14589/) (2020)
- [Multi-Fact Correction in Abstractive Text Summarization](https://mlsanity.com/paper/2010.02443/) (2020)
- [What Have We Achieved on Text Summarization?](https://mlsanity.com/paper/2010.04529/) (2020)
- [Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation](https://mlsanity.com/paper/2109.06379/) (2021)
- [FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization](https://mlsanity.com/paper/2205.07830/) (2022)
- [Focus Attention: Promoting Faithfulness and Diversity in Summarization](https://mlsanity.com/paper/2105.11921/) (2021)
- [Learning to Revise References for Faithful Summarization](https://mlsanity.com/paper/2204.10290/) (2022)
- [Factual Error Correction for Abstractive Summaries Using Entity Retrieval](https://mlsanity.com/paper/2204.08263/) (2022)

## Built on by (most cited first, 13 of 13)

- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning](https://mlsanity.com/paper/2312.10160/) (2023)
- [On Improving Summarization Factual Consistency from Natural Language Feedback](https://mlsanity.com/paper/2212.09968/) (2022)
- [Learning to Refine with Fine-Grained Natural Language Feedback](https://mlsanity.com/paper/2407.02397/) (2024)
- [Zero-shot Faithful Factual Error Correction](https://mlsanity.com/paper/2305.07982/) (2023)
- [Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs](https://mlsanity.com/paper/2311.00681/) (2023)
- [SWING: Balancing Coverage and Faithfulness for Dialogue Summarization](https://mlsanity.com/paper/2301.10483/) (2023)
- [MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration](https://mlsanity.com/paper/2503.15272/) (2025)
- [Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework](https://mlsanity.com/paper/2306.05119/) (2023)
- [Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization](https://mlsanity.com/paper/2305.14548/) (2023)
- [ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback](https://mlsanity.com/paper/2503.21332/) (2025)
- [Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze](https://mlsanity.com/paper/2402.08581/) (2024)
- [Mask-to-Correct^+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction](https://mlsanity.com/paper/2605.18776/) (2026)

## Abstract (arXiv)

State-of-the-art summarization models still struggle to be factually consistent with the input text. A model-agnostic way to address this problem is post-editing the generated summaries. However, existing approaches typically fail to remove entity errors if a suitable input entity replacement is not available or may insert erroneous content. In our work, we focus on removing extrinsic entity errors, or entities not in the source, to improve consistency while retaining the summary's essential information and form. We propose to use sentence-compression data to train the post-editing model to take a summary with extrinsic entity errors marked with special tokens and output a compressed, well-formed summary with those errors removed. We show that this model improves factual consistency while maintaining ROUGE, improving entity precision by up to 30% on XSum, and that this model can be applied on top of another post-editor, improving entity precision by up to a total of 38%. We perform an extensive comparison of post-editing approaches that demonstrate trade-offs between factual consistency, informativeness, and grammaticality, and we analyze settings where post-editors show the largest improvements.