mlsanityData to 14 Oct 2026

Text Editing by Command

arXiv 2010.12826 ↗First posted 24 Oct 2020cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

A prevailing paradigm in neural text generation is one-shot generation, where text is produced in a single step. The one-shot setting is inadequate, however, when the constraints the user wishes to impose on the generated text are dynamic, especially when authoring longer documents. We address this limitation with an interactive text generation setting in which the user interacts with the system by issuing commands to edit existing text. To this end, we propose a novel text editing task, and introduce WikiDocEdits, a dataset of single-sentence edits crawled from Wikipedia. We show that our Interactive Editor, a transformer-based model trained on this dataset, outperforms baselines and obtains positive results in both automatic and human evaluations. We present empirical and qualitative analyses of this model's performance.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 10; 2023: 12; 2024: 7; 2025: 2.

33 papers.

Sort:

By area:

  1. 2022Generating Sequences by Learning to Self-Correctcited by 277
  2. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 105
  3. 2022PEER: A Collaborative Language Modelcited by 86
  4. 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
  5. 2023CoEdIT: Text Editing by Task-Specific Instruction Tuningcited by 68
  6. 2023RewriteLM: An Instruction-Tuned Large Language Model for Text Rewritingcited by 67
  7. 2022Understanding Iterative Revision from Human-Written Textcited by 57
  8. 2023SummIt: Iterative Text Summarization via ChatGPTcited by 54
  9. 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Editscited by 49
  10. 2022Read, Revise, Repeat: A System Demonstration for Human-in-the-loop Iterative Text Revisioncited by 46
  11. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  12. 2023ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviewscited by 34
21 more
  1. 2024Automated Focused Feedback Generation for Scientific Writing Assistancecited by 33
  2. 2022Learning to Model Editing Processescited by 30
  3. 2023Second Thoughts are Best: Learning to Re-Align With Human Values from Text Editscited by 27
  4. 2022arXivEdits: Understanding the Human Revision Process in Scientific Writingcited by 26
  5. 2021Focused Attention Improves Document-Grounded Generationcited by 24
  6. 2024Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Toolscited by 13
  7. 2023Towards an On-device Agent for Text Rewritingcited by 7
  8. 2023XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updatescited by 6
  9. 2022LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-trainingcited by 5
  10. 2024Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologiescited by 5
  11. 2021Automatic Document Sketching: Generating Drafts from Analogous Textscited by 4
  12. 2023Personalized Abstractive Summarization by Tri-agent Generation Pipelinecited by 4
  13. 2024Patent-CR: A Dataset for Patent Claim Revisioncited by 4
  14. 2025StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Frameworkcited by 4
  15. 2022Claim Optimization in Computational Argumentationcited by 3
  16. 2023Interactive Text Generationcited by 2
  17. 2025Efficient Real-time Refinement of Language Model Text Generationcited by 2
  18. 2024Edisum: Summarizing and Explaining Wikipedia Edits at Scalecited by 1
  19. 2022Draft, Command, and Edit: Controllable Text Editing in E-Commercecited by 0
  20. 2023WikiIns: A High-Quality Dataset for Controlled Text Editing by Natural Language Instructioncited by 0
  21. 2023G-SPEED: General SParse Efficient Editing MoDelcited by 0