mlsanityData to 7 Oct 2026

Decontextualization: Making Sentences Stand-Alone

arXiv 2102.05169 ↗First posted 9 Feb 2021cs.CL cs.AIcited by 101

Not on the map. Why?

Abstract (arXiv)

Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context. Taking excerpts of text can be problematic, as key pieces may not be explicit in a local window. We isolate and define the problem of sentence decontextualization: taking a sentence together with its context and rewriting it to be interpretable out of context, while preserving its meaning. We describe an annotation procedure, collect data on the Wikipedia corpus, and use the data to train models to automatically decontextualize sentences. We present preliminary studies that show the value of sentence decontextualization in a user facing task, and as preprocessing for systems that perform document understanding. We argue that decontextualization is an important subtask in many downstream applications, and that the definitions and resources provided can benefit tasks that operate on sentences that occur in a richer context.

Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). Builds on 12 of its 34 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

12 of 34 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  6. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  7. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  8. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  9. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  10. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  11. 2016Neural Summarization by Extracting Sentences and Wordscited by 114
  12. 2016Improving Information Extraction by Acquiring External Evidence with Reinforcement Learningcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 16; 2023: 24; 2024: 21; 2025: 19; 2026: 10.

101 papers.

Sort:

By area:

  1. 2025LLMs Get Lost In Multi-Turn Conversationcited by 400
  2. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  3. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  4. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  5. 2023FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Setscited by 198
  6. 2021Towards Continual Knowledge Learning of Language Modelscited by 172
  7. 2021MultiVerS: Improving scientific claim verification with weak supervision and full-document contextcited by 140
  8. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 118
  9. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  10. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  11. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 96
  12. 2021QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehensioncited by 91
38 more
  1. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  2. 2023Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkerscited by 86
  3. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 82
  4. 2021Multi-Modal Answer Validation for Knowledge-Based VQAcited by 78
  5. 2021CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learningcited by 68
  6. 2022Generating Literal and Implied Subquestions to Fact-check Complex Claimscited by 66
  7. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chainscited by 63
  8. 2022Generating Scientific Claims for Zero-Shot Scientific Fact Checkingcited by 59
  9. 2022LENS: A Learnable Evaluation Metric for Text Simplificationcited by 54
  10. 2024Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Editscited by 49
  11. 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
  12. 2022Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusterscited by 44
  13. 2025ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubricscited by 44
  14. 2024Molecular Facts: Desiderata for Decontextualization in LLM Fact Verificationcited by 42
  15. 2023Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Tablecited by 40
  16. 2022EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Startcited by 35
  17. 2023Beyond the Chat: Executable and Verifiable Text-Editing with LLMscited by 35
  18. 2022Evaluating Factuality in Text Simplificationcited by 34
  19. 2024Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance?cited by 34
  20. 2022Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarizationcited by 32
  21. 2023Learning to Reject with a Fixed Predictor: Application to Decontextualizationcited by 32
  22. 2022PropSegmEnt: A Large-Scale Corpus for Proposition-Level Segmentation and Entailment Recognitioncited by 29
  23. 2023ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attackscited by 28
  24. 2024DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generationcited by 22
  25. 2022Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Modelcited by 20
  26. 2023Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representationscited by 19
  27. 2023SEMQA: Semi-Extractive Multi-Source Question Answeringcited by 19
  28. 2024Long-Form Answers to Visual Questions from Blind and Low Vision Peoplecited by 18
  29. 2025Towards Effective Extraction and Evaluation of Factual Claimscited by 18
  30. 2024EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generationcited by 17
  31. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 17
  32. 2023Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processescited by 15
  33. 2023A Question Answering Framework for Decontextualizing User-facing Snippets from Scientific Documentscited by 15
  34. 2024Core: Robust Factual Precision with Informative Sub-Claim Identificationcited by 15
  35. 2024InfoLossQA: Characterizing and Recovering Information Loss in Text Simplificationcited by 14
  36. 2025QUDsim: Quantifying Discourse Similarities in LLM-Generated Textcited by 13
  37. 2025LAQuer: Localized Attribution Queries in Content-grounded Generationcited by 13
  38. 2022Cross-document Event Coreference Search: Task, Dataset and Modelingcited by 12

50 most cited of 101 All 101 (JSON)