mlsanityData to 7 Oct 2026

Nearest Neighbor Machine Translation

arXiv 2010.00710 ↗First posted 1 Oct 2020cs.CLcited by 209

Not on the map. Why?

Cited by 39 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce k-nearest-neighbor machine translation (kNN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. This approach requires no additional training and scales to give the decoder direct access to billions of examples at test time, resulting in a highly expressive model that consistently improves performance across many settings. Simply adding nearest neighbor search improves a state-of-the-art German-English translation model by 1.5 BLEU. kNN-MT allows a single model to be adapted to diverse domains by using a domain-specific datastore, improving results by an average of 9.2 BLEU over zero-shot transfer, and achieving new state-of-the-art results -- without training on these domains. A massively multilingual model can also be specialized for particular language pairs, with improvements of 3 BLEU for translating from English into German and Chinese. Qualitatively, kNN-MT is easily interpretable; it combines source and target context to retrieve highly relevant examples.

Key facts. Cited by 209 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 51; 2023: 54; 2024: 41; 2025: 19; 2026: 10.

209 papers.

Sort:

By area:

  1. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  3. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  5. 2021BASE Layers: Simplifying Training of Large, Sparse Modelscited by 315
  6. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  7. 2021Internet-Augmented Dialogue Generationcited by 217
  8. 2022In-context Examples Selection for Machine Translationcited by 172
  9. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  10. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 144
  11. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  12. 2022Training Language Models with Memory Augmentationcited by 112
38 more
  1. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  2. 2023Text Classification via Large Language Modelscited by 104
  3. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  4. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  5. 2021Efficient Nearest Neighbor Language Modelscited by 93
  6. 2021Adaptive Semiparametric Language Modelscited by 83
  7. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 82
  8. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  9. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  10. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  11. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  12. 2023Self-Knowledge Guided Retrieval Augmentation for Large Language Modelscited by 69
  13. 2022Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Modelscited by 63
  14. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  15. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  16. 2021Adaptive Nearest Neighbor Machine Translationcited by 58
  17. 2021Personalized Federated Learning through Local Memorizationcited by 57
  18. 2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
  19. 2023kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inferencecited by 47
  20. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  21. 2022Retrieval-Enhanced Machine Learningcited by 46
  22. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  23. 2021Fast Nearest Neighbor Machine Translationcited by 37
  24. 2022Semi-Parametric Neural Image Synthesiscited by 36
  25. 2022Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learningcited by 36
  26. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  27. 2024MeaCap: Memory-Augmented Zero-shot Image Captioningcited by 35
  28. 2022Knowledge Base Question Answering by Case-based Reasoning over Subgraphscited by 31
  29. 2021How BPE Affects Memorization in Transformerscited by 29
  30. 2023Why do Nearest Neighbor Language Models Work?cited by 29
  31. 2024PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-designcited by 28
  32. 2021GNN-LM: Language Modeling based on Global Contexts via GNNcited by 27
  33. 2022kNN-Prompt: Nearest Neighbor Zero-Shot Inferencecited by 27
  34. 2021Learning Kernel-Smoothed Machine Translation with Retrieved Examplescited by 25
  35. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  36. 2022Relational Memory Augmented Language Modelscited by 24
  37. 2022Efficient Cluster-Based k-Nearest-Neighbor Machine Translationcited by 24
  38. 2022Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibrationcited by 24

50 most cited of 209 All 209 (JSON)