mlsanityData to 7 Oct 2026

LenAtten: An Effective Length Controlling Unit For Text Summarization

arXiv 2106.00316 ↗First posted 1 Jun 2021cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit, causing a compromise between length controllability and summary quality. In this work, we present an effective length controlling unit Length Attention (LenAtten) to break this trade-off. Experimental results show that LenAtten not only brings improvements in length controllability and ROGUE scores but also has great generalization ability. In the task of generating a summary with the target length, our model is 732 times better than the best-performing length controllable summarizer in length controllability on the CNN/Daily Mail dataset.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

14 of 22 references.

References · 14

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  4. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  5. 2019Text Summarization with Pretrained Encoderscited by 553
  6. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  7. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
  8. 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 345
  9. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  10. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  11. 2020Extractive Summarization as Text Matchingcited by 189
  12. 2017Controllable Abstractive Summarizationcited by 110
2 more
  1. 2016Controlling Output Length in Neural Encoder-Decoderscited by 75
  2. 2019Positional Encoding to Control Output Sequence Lengthcited by 56

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 4; 2026: 1.

14 papers.

Sort:

By area:

  1. 2024Prompt-Based Length Controlled Generation with Multiple Control Typescited by 19
  2. 2023Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Surveycited by 18
  3. 2023Prompt-Based Length Controlled Generation with Reinforcement Learningcited by 14
  4. 2024Zero-Shot Strategies for Length-Controllable Summarizationcited by 10
  5. 2024Length Controlled Generation for Black-box LLMscited by 8
  6. 2023Summarization with Precise Length Controlcited by 4
  7. 2025Prompt-Based One-Shot Exact Length-Controlled Generation with LLMscited by 4
  8. 2026Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulationcited by 4
  9. 2025Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimizationcited by 3
  10. 2024Fine-grained length controllable video captioning with ordinal embeddingscited by 2
  11. 2024Hansel: Output Length Controlling Framework for Large Language Modelscited by 2
  12. 2023Unsupervised Extractive Summarization with Learnable Length Control Strategiescited by 1
2 more
  1. 2025Controlling Summarization Length Through EOS Token Weightingcited by 1
  2. 2025Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generationcited by 0