mlsanityData to 7 Oct 2026

Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text

arXiv 2107.03444 ↗First posted 7 Jul 2021cs.CLcited by 45

Not on the map. Why?

Abstract (arXiv)

This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplicity. We train the model with a novel algorithm to optimize the reward (k-SCST), in which the model proposes several candidate simplifications, computes each candidate's reward, and encourages candidates that outperform the mean reward. Finally, we propose a realistic text comprehension task as an evaluation method for text simplification. When tested on the English news domain, the KiS model outperforms strong supervised baselines by more than 4 SARI points, and can help people complete a comprehension task an average of 18% faster while retaining accuracy, when compared to the original text. Code available: https://github.com/tingofurro/keep_it_simple

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 19 of its 53 references that are in the map. First posted on arXiv 7 Jul 2021.

Builds on

19 of 53 references.

References · 19

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  3. 2016Self-critical Sequence Training for Image Captioningcited by 544
  4. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  5. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  6. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  7. 2017Sentence Simplification with Deep Reinforcement Learningcited by 107
  8. 2019Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reportscited by 96
  9. 2019Controllable Sentence Simplificationcited by 78
  10. 2020What Have We Achieved on Text Summarization?cited by 65
  11. 2019EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editingcited by 63
  12. 2019Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answeringcited by 63
7 more
  1. 2020Seq2Edits: Sequence Transduction Using Span-level Edit Operationscited by 58
  2. 2018Deep Communicating Agents for Abstractive Summarizationcited by 50
  3. 2018Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!cited by 43
  4. 2018Unsupervised Neural Text Simplificationcited by 29
  5. 2021The Summary Loop: Learning to Write Abstractive Summaries Without Examplescited by 27
  6. 2018Dynamic Multi-Level Multi-Task Learning for Sentence Simplificationcited by 25
  7. 2019Discourse Level Factors for Sentence Deletion in Text Simplificationcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 16; 2024: 11; 2025: 10; 2026: 2.

45 papers.

Sort:

By area:

  1. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
  2. 2023Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defensecited by 401
  3. 2023ChatGPT as a Factual Inconsistency Evaluator for Text Summarizationcited by 75
  4. 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 65
  5. 2024Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inferencecited by 51
  6. 2023Discrete Prompt Compression with Reinforcement Learningcited by 42
  7. 2023Beyond the Chat: Executable and Verifiable Text-Editing with LLMscited by 35
  8. 2022Evaluating Factuality in Text Simplificationcited by 34
  9. 2023A Better Way to Do Masked Language Model Scoringcited by 27
  10. 2023Generating Summaries with Controllable Readability Levelscited by 24
  11. 2022Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processingcited by 23
  12. 2023Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Modelcited by 21
33 more
  1. 2022Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learningcited by 18
  2. 2023Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehensioncited by 16
  3. 2023Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSAcited by 15
  4. 2023SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pagescited by 12
  5. 2024SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generationcited by 12
  6. 2024Authorship Style Transfer with Policy Optimizationcited by 11
  7. 2023Teaching the Pre-trained Model to Generate Simple Texts for Text Simplificationcited by 10
  8. 2024Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generationcited by 10
  9. 2024Keep It Private: Unsupervised Privatization of Online Textcited by 10
  10. 2025An Empirical Study on Prompt Compression for Large Language Modelscited by 8
  11. 2023Exploiting Summarization Data to Help Text Simplificationcited by 5
  12. 2024An LLM-Enhanced Adversarial Editing System for Lexical Simplificationcited by 5
  13. 2024Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservationcited by 5
  14. 2024TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methodscited by 5
  15. 2025Progressive Document-level Text Simplification via Large Language Modelscited by 5
  16. 2025Steering Large Language Models with Register Analysis for Arbitrary Style Transfercited by 5
  17. 2023Automatic and Human-AI Interactive Text Generationcited by 4
  18. 2024Style Transfer with Multi-iteration Preference Optimizationcited by 4
  19. 2025EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuningcited by 4
  20. 2025Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymizationcited by 4
  21. 2024Digital Comprehensibility Assessment of Simplified Texts among Persons with Intellectual Disabilitiescited by 3
  22. 2025Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisitioncited by 3
  23. 2025ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Modelscited by 3
  24. 2022Unsupervised Sentence Simplification via Dependency Parsingcited by 2
  25. 2022Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasetscited by 1
  26. 2024PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Modelscited by 1
  27. 2026Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDAcited by 1
  28. 2023SimCSum: Joint Learning of Simplification and Cross-lingual Summarization for Cross-lingual Science Journalismcited by 0
  29. 2023Can Knowledge Graphs Simplify Text?cited by 0
  30. 2025Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptorcited by 0
  31. 2025Toward Machine Interpreting: Lessons from Human Interpreting Studiescited by 0
  32. 2025Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cyclescited by 0
  33. 2026PlainMedScale: A Corpus of Multi-Level Simplified Medical Texts in German and Englishcited by 0