mlsanityData to 14 Oct 2026

A Retrieve-and-Edit Framework for Predicting Structured Outputs

arXiv 1812.01194 ↗First posted 4 Dec 2018stat.ML cs.LGcited by 73

Not on the map. Why?

Abstract (arXiv)

For the task of generating complex outputs such as source code, editing existing outputs can be easier than generating complex outputs from scratch. With this motivation, we propose an approach that first retrieves a training example based on the input (e.g., natural language description) and then edits it to the desired output (e.g., code). Our contribution is a computationally efficient method for learning a retrieval model that embeds the input in a task-dependent way without relying on a hand-crafted metric or incurring the expense of jointly training the retriever with the editor. Our retrieve-and-edit framework can be applied on top of any base model. We show that on a new autocomplete task for GitHub Python code and the Hearthstone cards benchmark, retrieve-and-edit significantly boosts the performance of a vanilla sequence-to-sequence model on both tasks.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 2; 2021: 19; 2022: 23; 2023: 12; 2024: 12; 2025: 4; 2026: 1.

73 papers.

Sort:

By area:

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  3. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  5. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 163
  6. 2022A Survey on Retrieval-Augmented Text Generationcited by 158
  7. 2022DocPrompting: Generating Code by Retrieving the Docscited by 153
  8. 2021Retrieval Augmented Code Generation and Summarizationcited by 149
  9. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125
  10. 2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 119
  11. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  12. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
38 more
  1. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  2. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 85
  3. 2021Improving Named Entity Recognition by External Context Retrieving and Cooperative Learningcited by 76
  4. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  5. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  6. 2024Revisiting Demonstration Selection Strategies in In-Context Learningcited by 58
  7. 2022Compilable Neural Code Generation with Compiler Feedbackcited by 47
  8. 2022Retrieval-Enhanced Machine Learningcited by 47
  9. 2022CoditT5: Pretraining for Source Code and Natural Language Editingcited by 45
  10. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 44
  11. 2024Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completioncited by 40
  12. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  13. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
  14. 2022Knowledge Base Question Answering by Case-based Reasoning over Subgraphscited by 31
  15. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  16. 2023PoET: A generative model of protein families as sequences-of-sequencescited by 29
  17. 2023Copy Is All You Needcited by 27
  18. 2022Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuningcited by 25
  19. 2023AceCoder: Utilizing Existing Code to Enhance Code Generationcited by 25
  20. 2021Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioningcited by 23
  21. 2021RetGen: A Joint framework for Retrieval and Grounded Text Generation Modelingcited by 22
  22. 2022AmbiPun: Generating Humorous Puns with Ambiguous Contextcited by 21
  23. 2022ExPUNations: Augmenting Puns with Keywords and Explanationscited by 21
  24. 2022NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challengecited by 20
  25. 2025RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learningcited by 20
  26. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunitiescited by 18
  27. 2021SHARE: a System for Hierarchical Assistive Recipe Editingcited by 15
  28. 2024Accelerating Retrieval-Augmented Generationcited by 14
  29. 2024MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generationcited by 13
  30. 2022Incorporating Domain Knowledge through Task Augmentation for Front-End JavaScript Code Generationcited by 11
  31. 2022A Unified Framework for Pun Generation with Humor Principlescited by 10
  32. 2023De-fine: Decomposing and Refining Visual Programs with Auto-Feedbackcited by 10
  33. 2024Retrieval is Accurate Generationcited by 10
  34. 2022TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledgecited by 9
  35. 2021Capturing Structural Locality in Non-parametric Language Modelscited by 8
  36. 2022Fix Bugs with Transformer through a Neural-Symbolic Edit Grammarcited by 8
  37. 2024VIMI: Grounding Video Generation through Multi-modal Instructioncited by 8
  38. 2022Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parserscited by 7

50 most cited of 73 All 73 (JSON)