mlsanityData to 14 Oct 2026

Translation in the Wild

arXiv 2505.23548 ↗First posted 29 May 2025cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) excel in translation among other things, demonstrating competitive performance for many language pairs in zero- and few-shot settings. But unlike dedicated neural machine translation models, LLMs are not trained on any translation-related objective. What explains their remarkable translation abilities? Are these abilities grounded in "incidental bilingualism" (Briakou et al. 2023) in training data? Does instruction tuning contribute to it? Are LLMs capable of aligning and leveraging semantically identical or similar monolingual contents from different corners of the internet that are unlikely to fit in a single context window? I offer some reflections on this topic, informed by recent studies and growing user experience. My working hypothesis is that LLMs' translation abilities originate in two different types of pre-training data that may be internalized by the models in different ways. I discuss the prospects for testing the "duality" hypothesis empirically and its implications for reconceptualizing translation, human and machine, in the age of deep learning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 60 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

38 of 60 references.

References · 38

  1. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  4. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  5. 2022A Survey on In-context Learningcited by 721
  6. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  7. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 469
  8. 2024Do Llamas Work in English? On the Latent Language of Multilingual Transformerscited by 281
  9. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  10. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 243
  11. 2019Emerging Cross-lingual Structure in Pretrained Language Modelscited by 181
  12. 2024Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuningcited by 177
26 more
  1. 2023Multilingual Machine Translation with Large Language Models: Empirical Results and Analysiscited by 160
  2. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 145
  3. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
  4. 2023The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluationcited by 95
  5. 2022Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Modelscited by 92
  6. 2023Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Modelscited by 87
  7. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
  8. 2023Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capabilitycited by 62
  9. 2025Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languagescited by 59
  10. 2023Leveraging GPT-4 for Automatic Translation Post-Editingcited by 56
  11. 2023Exploring Human-Like Translation Strategy with Large Language Modelscited by 44
  12. 2024TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinementcited by 39
  13. 2025Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Studycited by 38
  14. 2024A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelismcited by 35
  15. 2023ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedbackcited by 34
  16. 2024Translating Step-by-Step: Decomposing the Translation Process for Improved Translation Quality of Long-Form Textscited by 31
  17. 2022English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddingscited by 26
  18. 2024Guiding Large Language Models to Post-Edit Machine Translation with Error Annotationscited by 22
  19. 2024mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?cited by 21
  20. 2023Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddingscited by 19
  21. 2024xTower: A Multilingual LLM for Explaining and Correcting Translation Errorscited by 17
  22. 2025Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translationcited by 14
  23. 2024Creative and Context-Aware Translation of East Asian Idioms with GPT-4cited by 10
  24. 2025Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes Fromcited by 4
  25. 2025Translation Analytics for Freelancers: I. Introduction, Data Preparation, Baseline Evaluationscited by 2
  26. 2025Sociotechnical Effects of Machine Translationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RLcited by 2
  2. 2026Translation Indeterminacy and the Distributional Fallacycited by 0