# Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

arXiv: https://arxiv.org/abs/1810.06065 · HTML: https://mlsanity.com/paper/1810.06065/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2018.

## Built on by (most cited first, 8 of 8)

- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2108.02859/) (2021)
- [Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation](https://mlsanity.com/paper/2103.10918/) (2021)
- [Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing](https://mlsanity.com/paper/2406.03993/) (2024)
- [Estimation of Summary-to-Text Inconsistency by Mismatched Embeddings](https://mlsanity.com/paper/2104.05156/) (2021)
- [Consistency and Coherence from Points of Contextual Similarity](https://mlsanity.com/paper/2112.11638/) (2021)
- [Augmented Abstractive Summarization With Document-LevelSemantic Graph](https://mlsanity.com/paper/2109.06046/) (2021)

## Abstract (arXiv)

Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vulnerable to adversarial information, suggesting a crucial lack of semantic understanding. In this paper, we propose a novel semantic-aware neural abstractive summarization model that learns to generate high quality summaries through semantic interpretation over salient content. A novel evaluation scheme with adversarial samples is introduced to measure how well a model identifies off-topic information, where our model yields significantly better performance than the popular pointer-generator summarizer. Human evaluation also confirms that our system summaries are uniformly more informative and faithful as well as less redundant than the seq2seq model.