mlsanityData to 7 Oct 2026

Source Identification in Abstractive Summarization

arXiv 2402.04677 ↗First posted 7 Feb 2024cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Neural abstractive summarization models make summaries in an end-to-end manner, and little is known about how the source information is actually converted into summaries. In this paper, we define input sentences that contain essential information in the generated summary as textitsource sentences and study how abstractive summaries are made by analyzing the source sentences. To this end, we annotate source sentences for reference summaries and system summaries generated by PEGASUS on document-summary pairs sampled from the CNN/DailyMail and XSum datasets. We also formulate automatic source sentence detection and compare multiple methods to establish a strong baseline for the task. Experimental results show that the perplexity-based method performs well in highly abstractive settings, while similarity-based methods perform robustly in relatively extractive settings. Our code and data are available at https://github.com/suhara/sourcesum.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 28 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

23 of 28 references.

References · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  4. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  7. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  8. 2019Text Summarization with Pretrained Encoderscited by 553
  9. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  10. 2019Neural Text Summarization: A Critical Evaluationcited by 189
  11. 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
  12. 2021Improving Factual Consistency of Abstractive Summarization via Question Answeringcited by 55
11 more
  1. 2019Scoring Sentence Singletons and Pairs for Abstractive Summarizationcited by 34
  2. 2021Unsupervised Extractive Summarization using Pointwise Mutual Informationcited by 23
  3. 2019Analyzing Sentence Fusion in Abstractive Summarizationcited by 19
  4. 2020Understanding Points of Correspondence between Sentences for Abstractive Summarizationcited by 16
  5. 2020Learning to Fuse Sentences with Transformers for Summarizationcited by 14
  6. 2022Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Treescited by 14
  7. 2021SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarizationcited by 13
  8. 2019Understanding Multi-Head Attention in Abstractive Summarizationcited by 12
  9. 2021Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLGcited by 11
  10. 2021Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attributioncited by 10
  11. 2021Summary Explorer: Visualizing the State of the Art in Text Summarizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversationscited by 1
  2. 2026From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarizationcited by 1