mlsanityData to 7 Oct 2026

DiffuSum: Generation Enhanced Extractive Summarization with Diffusion

arXiv 2305.01735 ↗First posted 2 May 2023cs.CLcited by 25

Not on the map. Why?

Abstract (arXiv)

Extractive summarization aims to form a summary by directly extracting sentences from the source document. Existing works mostly formulate it as a sequence labeling problem by making individual sentence label predictions. This paper proposes DiffuSum, a novel paradigm for extractive summarization, by directly generating the desired summary sentence representations with diffusion models and extracting sentences based on sentence representation matching. In addition, DiffuSum jointly optimizes a contrastive sentence encoder with a matching loss for sentence representation alignment and a multi-class contrastive loss for representation diversity. Experimental results show that DiffuSum achieves the new state-of-the-art extractive results on CNN/DailyMail with ROUGE scores of 44.83/22.56/40.56. Experiments on the other two datasets with different summary lengths also demonstrate the effectiveness of DiffuSum. The strong performance of our framework shows the great potential of adapting generative models for extractive summarization. To encourage more following work in the future, we have released our codes at urlhttps://github.com/hpzhang94/DiffuSum

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 36 of its 47 references that are in the map. First posted on arXiv 2 May 2023.

Builds on

36 of 47 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2022Video Diffusion Modelscited by 2,280
  9. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  10. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  12. 2015Teaching Machines to Read and Comprehendcited by 1,039
24 more
  1. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  2. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  3. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  4. 2019Text Summarization with Pretrained Encoderscited by 553
  5. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  6. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Modelscited by 439
  7. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  8. 2022Continuous diffusion for categorical datacited by 202
  9. 2020Extractive Summarization as Text Matchingcited by 189
  10. 2021A Unified Generative Framework for Various NER Subtaskscited by 141
  11. 2018Ranking Sentences for Extractive Summarization with Reinforcement Learningcited by 128
  12. 2019HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarizationcited by 120
  13. 2016Neural Summarization by Extracting Sentences and Wordscited by 114
  14. 2022Self-conditioned Embedding Diffusion for Text Generationcited by 114
  15. 2020Heterogeneous Graph Neural Networks for Extractive Document Summarizationcited by 90
  16. 2022SeqDiffuSeq: Text Diffusion with Encoder-Decoder Transformerscited by 63
  17. 2023Extractive Summarization via ChatGPT for Faithful Summary Generationcited by 58
  18. 2018Neural Document Summarization by Jointly Learning to Score and Select Sentencescited by 56
  19. 2019Searching for Effective Neural Extractive Summarization: What Works and What's Nextcited by 38
  20. 2020Augmented Natural Language for Generative Sequence Labelingcited by 29
  21. 2022HEGEL: Hypergraph Transformer for Long Document Summarizationcited by 28
  22. 2019Summary Level Training of Sentence Rewriting for Abstractive Summarizationcited by 23
  23. 2022Improving the Faithfulness of Abstractive Summarization via Entity Coverage Controlcited by 21
  24. 2022COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarizationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 9; 2025: 5; 2026: 1.

25 papers.

Sort:

By area:

  1. 2025A Survey on Diffusion Language Modelscited by 75
  2. 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Stepscited by 71
  3. 2023Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimizationcited by 56
  4. 2023SummIt: Iterative Text Summarization via ChatGPTcited by 53
  5. 2024A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Modelscited by 52
  6. 2024V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuningcited by 45
  7. 2023DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Modelscited by 36
  8. 2024Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategycited by 17
  9. 2023A Survey of Diffusion Models in Natural Language Processingcited by 16
  10. 2023Instruction Position Matters in Sequence Generation with Large Language Modelscited by 10
  11. 2023Contrastive Hierarchical Discourse Graph for Scientific Document Summarizationcited by 9
  12. 2024DiffLM: Controllable Synthetic Data Generation via Diffusion Language Modelscited by 9
13 more
  1. 2023InfoDiffusion: Information Entropy Aware Diffusion Process for Non-Autoregressive Text Generationcited by 5
  2. 2024AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preferencecited by 4
  3. 2024DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarizationcited by 4
  4. 2024Prompt-tuning for Clickbait Detection via Text Summarizationcited by 3
  5. 2025Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoningcited by 3
  6. 2023Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extractioncited by 2
  7. 2023Unsupervised Multi-document Summarization with Holistic Inferencecited by 2
  8. 2024LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reportscited by 2
  9. 2024Reward-based Input Construction for Cross-document Relation Extractioncited by 1
  10. 2025Understanding the Quality-Diversity Trade-off in Diffusion Language Modelscited by 1
  11. 2025OrderSum: Semantic Sentence Ordering for Extractive Summarizationcited by 0
  12. 2025Chain of Summaries: Summarization Through Iterative Questioningcited by 0
  13. 2026Efficient Extractive Summarization with MAMBA-Transformer Hybrids for Low-Resource Scenarioscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Discrete Diffusion Language Model for Efficient Text Summarization
  2. 2019Mixture Content Selection for Diverse Sequence Generation
  3. 2026SVD-RAG: Efficient Tree-Organized Retrieval-Augmented Generation via Singular Value Decomposition
  4. 2024Information-Theoretic Distillation for Reference-less Summarization
  5. 2023PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
  6. 2025State Space Models for Extractive Summarization in Low Resource Scenarios
  7. 2024LOCOST: State-Space Models for Long Document Abstractive Summarization
  8. 2024Video Summarization using Denoising Diffusion Probabilistic Model