# Analyzing Sentence Fusion in Abstractive Summarization

arXiv: https://arxiv.org/abs/1910.00203 · HTML: https://mlsanity.com/paper/1910.00203/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 19 of 19)

- [Annotating and Modeling Fine-grained Factuality in Summarization](https://mlsanity.com/paper/2104.04302/) (2021)
- [Attribute First, then Generate: Locally-attributable Grounded Text Generation](https://mlsanity.com/paper/2403.17104/) (2024)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Learning to Revise References for Faithful Summarization](https://mlsanity.com/paper/2204.10290/) (2022)
- [Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2108.02859/) (2021)
- [QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions](https://mlsanity.com/paper/2109.12655/) (2021)
- [StreamHover: Livestream Transcript Summarization and Annotation](https://mlsanity.com/paper/2109.05160/) (2021)
- [A Sliding-Window Approach to Automatic Creation of Meeting Minutes](https://mlsanity.com/paper/2104.12324/) (2021)
- [A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarization](https://mlsanity.com/paper/2303.03948/) (2023)
- [A New Approach to Overgenerating and Scoring Abstractive Summaries](https://mlsanity.com/paper/2104.01726/) (2021)
- [A Modular Approach for Multimodal Summarization of TV Shows](https://mlsanity.com/paper/2403.03823/) (2024)
- [Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution](https://mlsanity.com/paper/2106.01518/) (2021)
- [Controlled Text Reduction](https://mlsanity.com/paper/2210.13449/) (2022)
- [Leveraging Locality in Abstractive Text Summarization](https://mlsanity.com/paper/2205.12476/) (2022)
- [Towards Summary Candidates Fusion](https://mlsanity.com/paper/2210.08779/) (2022)
- [How "Multi" is Multi-Document Summarization?](https://mlsanity.com/paper/2210.12688/) (2022)
- [What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization](https://mlsanity.com/paper/2305.07615/) (2023)
- [Source Identification in Abstractive Summarization](https://mlsanity.com/paper/2402.04677/) (2024)
- [Evaluating Whether LLMs Can Reliably Connect the DOTs?](https://mlsanity.com/paper/2609.38406/) (2026)

## Abstract (arXiv)

While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.