mlsanityData to 14 Oct 2026

Controlling Output Length in Neural Encoder-Decoders

arXiv 1609.09552 ↗First posted 30 Sep 2016cs.CLcited by 75

Not on the map. Why?

Abstract (arXiv)

Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial for applications such as text summarization, in which we have to generate concise summaries with a desired length. In this paper, we propose methods for controlling the output sequence length for neural encoder-decoder models: two decoding-based methods and two learning-based methods. Results show that our learning-based methods have the capability to control length without degrading summary quality in a summarization task.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 21; 2022: 21; 2023: 16; 2024: 6; 2025: 8; 2026: 3.

75 papers.

Sort:

By area:

  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  2. 2023A Long Way to Go: Investigating Length Correlations in RLHFcited by 291
  3. 2021Aspect-Controllable Opinion Summarizationcited by 47
  4. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  5. 2021Data-to-text Generation with Macro Planningcited by 34
  6. 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
  7. 2021Control Prefixes for Parameter-Efficient Text Generationcited by 24
  8. 2022EntSUM: A Data Set for Entity-Centric Summarizationcited by 22
  9. 2023Improving Pacing in Long-Form Story Planningcited by 21
  10. 2022Why is constrained neural language generation particularly challenging?cited by 19
  11. 2021Deep Extrapolation for Attribute-Enhanced Generationcited by 18
  12. 2021Machine Translation Verbosity Control for Automatic Dubbingcited by 18
38 more
  1. 2023Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Surveycited by 18
  2. 2021Controllable Summarization with Constrained Markov Decision Processcited by 17
  3. 2023"Why is this misleading?": Detecting News Headline Hallucinations with Explanationscited by 17
  4. 2023From Chaos to Clarity: Claim Normalization to Empower Fact-Checkingcited by 17
  5. 2021LenAtten: An Effective Length Controlling Unit For Text Summarizationcited by 14
  6. 2022Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillationcited by 14
  7. 2021Text Compression-aided Transformer Encodingcited by 13
  8. 2021A New Approach to Overgenerating and Scoring Abstractive Summariescited by 13
  9. 2021Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairnesscited by 12
  10. 2022Context-Tuning: Learning Contextualized Prompts for Natural Language Generationcited by 12
  11. 2023Learning Combinatorial Prompts for Universal Controllable Image Captioningcited by 12
  12. 2026WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoningcited by 12
  13. 2021Lost in Interpreting: Speech Translation from Source or Interpreter?cited by 10
  14. 2021Style Control for Schema-Guided Natural Language Generationcited by 10
  15. 2022Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Rewardcited by 10
  16. 2022Time-aware Prompting for Text Generationcited by 10
  17. 2024Zero-Shot Strategies for Length-Controllable Summarizationcited by 10
  18. 2025ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructionscited by 10
  19. 2022Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoningcited by 8
  20. 2022"What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generationcited by 7
  21. 2022Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documentscited by 7
  22. 2022FAST: Improving Controllability for Text Generation with Feedback Aware Self-Trainingcited by 7
  23. 2022Controlled Language Generation for Language Learning Itemscited by 7
  24. 2023CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generationcited by 7
  25. 2023Toward Unified Controllable Text Generation via Regular Expression Instructioncited by 7
  26. 2021Progressive Open-Domain Response Generation with Multiple Controllable Attributescited by 6
  27. 2022A Focused Study on Sequence Length for Dialogue Summarizationcited by 6
  28. 2022Latent Prompt Tuning for Text Summarizationcited by 6
  29. 2023The Current State of Summarizationcited by 6
  30. 2021Unifying Cross-lingual Summarization and Machine Translation with Compression Ratecited by 5
  31. 2022Unsupervised Multi-Granularity Summarizationcited by 5
  32. 2023ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oraclescited by 5
  33. 2021Neural Rule-Execution Tracking Machine For Transformer-Based Text Generationcited by 4
  34. 2022Revision for Concision: A Constrained Paraphrase Generation Taskcited by 4
  35. 2022Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing Generationcited by 4
  36. 2022(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplificationcited by 4
  37. 2023Summarization with Precise Length Controlcited by 4
  38. 2023Controlled Text Generation with Hidden Representation Transformationscited by 4

50 most cited of 75 All 75 (JSON)