# To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text

arXiv: https://arxiv.org/abs/2106.01581 · HTML: https://mlsanity.com/paper/2106.01581/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 3 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (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)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [GSum: A General Framework for Guided Neural Abstractive Summarization](https://mlsanity.com/paper/2010.08014/) (2020)
- [Do Massively Pretrained Language Models Make Better Storytellers?](https://mlsanity.com/paper/1909.10705/) (2019)
- [ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Tasks](https://mlsanity.com/paper/1803.01937/) (2018)
- [Learning to Summarize Radiology Findings](https://mlsanity.com/paper/1809.04698/) (2018)
- [Understanding Neural Abstractive Summarization Models via Uncertainty](https://mlsanity.com/paper/2010.07882/) (2020)
- [Quantity doesn't buy quality syntax with neural language models](https://mlsanity.com/paper/1909.00111/) (2019)

## Built on by (most cited first, 5 of 5)

- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization](https://mlsanity.com/paper/2108.13684/) (2021)
- [How Far are We from Robust Long Abstractive Summarization?](https://mlsanity.com/paper/2210.16732/) (2022)
- [ComSum: Commit Messages Summarization and Meaning Preservation](https://mlsanity.com/paper/2108.10763/) (2021)
- [LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation](https://mlsanity.com/paper/2604.25665/) (2026)

## Abstract (arXiv)

Abstractive neural summarization models have seen great improvements in recent years, as shown by ROUGE scores of the generated summaries. But despite these improved metrics, there is limited understanding of the strategies different models employ, and how those strategies relate their understanding of language. To understand this better, we run several experiments to characterize how one popular abstractive model, the pointer-generator model of See et al. (2017), uses its explicit copy/generation switch to control its level of abstraction (generation) vs extraction (copying). On an extractive-biased dataset, the model utilizes syntactic boundaries to truncate sentences that are otherwise often copied verbatim. When we modify the copy/generation switch and force the model to generate, only simple paraphrasing abilities are revealed alongside factual inaccuracies and hallucinations. On an abstractive-biased dataset, the model copies infrequently but shows similarly limited abstractive abilities. In line with previous research, these results suggest that abstractive summarization models lack the semantic understanding necessary to generate paraphrases that are both abstractive and faithful to the source document.