# Enhancing Factual Consistency of Abstractive Summarization

arXiv: https://arxiv.org/abs/2003.08612 · HTML: https://mlsanity.com/paper/2003.08612/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [Improving Factual Consistency of Abstractive Summarization via Question Answering](https://mlsanity.com/paper/2105.04623/) (2021)
- [Generative Knowledge Graph Construction: A Review](https://mlsanity.com/paper/2210.12714/) (2022)
- [Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs](https://mlsanity.com/paper/2104.08400/) (2021)
- [Enhancing Scientific Papers Summarization with Citation Graph](https://mlsanity.com/paper/2104.03057/) (2021)
- [Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation](https://mlsanity.com/paper/2103.10918/) (2021)
- [Leveraging Information Bottleneck for Scientific Document Summarization](https://mlsanity.com/paper/2110.01280/) (2021)
- [Analysis of Multidomain Abstractive Summarization Using Salience Allocation](https://mlsanity.com/paper/2402.11955/) (2024)
- [KATSum: Knowledge-aware Abstractive Text Summarization](https://mlsanity.com/paper/2212.03371/) (2022)

## Abstract (arXiv)

Automatic abstractive summaries are found to often distort or fabricate facts in the article. This inconsistency between summary and original text has seriously impacted its applicability. We propose a fact-aware summarization model FASum to extract and integrate factual relations into the summary generation process via graph attention. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems. Empirical results show that the fact-aware summarization can produce abstractive summaries with higher factual consistency compared with existing systems, and the correction model improves the factual consistency of given summaries via modifying only a few keywords.