mlsanityData to 7 Oct 2026

Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?

arXiv 2409.19151 ↗First posted 27 Sep 2024cs.CLcited by 23

Not on the map. Why?

Abstract (arXiv)

Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from One Book (Tanzer et al., 2024) suggests that prompting long-context LLMs with one grammar book enables English-Kalamang translation, an XLR language unseen by LLMs - a noteworthy case of linguistics helping an NLP task. We investigate the source of this translation ability, finding almost all improvements stem from the book's parallel examples rather than its grammatical explanations. We find similar results for Nepali and Guarani, seen low-resource languages, and we achieve performance comparable to an LLM with a grammar book by simply fine-tuning an encoder-decoder translation model. We then investigate where grammar books help by testing two linguistic tasks, grammaticality judgment and gloss prediction, and we explore what kind of grammatical knowledge helps by introducing a typological feature prompt that achieves leading results on these more relevant tasks. We thus emphasise the importance of task-appropriate data for XLR languages: parallel examples for translation, and grammatical data for linguistic tasks. As we find no evidence that long-context LLMs can make effective use of grammatical explanations for XLR translation, we conclude data collection for multilingual XLR tasks such as translation is best focused on parallel data over linguistic description.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 32 of its 71 references that are in the map. First posted on arXiv 27 Sep 2024.

Builds on

32 of 71 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  6. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  7. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  8. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  9. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 504
  10. 2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 88
  11. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  12. 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 74
20 more
  1. 2024LLMs Are Few-Shot In-Context Low-Resource Language Learnerscited by 68
  2. 2018Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processingcited by 63
  3. 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
  4. 2017Learning Language Representations for Typology Predictioncited by 40
  5. 2022Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scalecited by 40
  6. 2024Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuraciescited by 40
  7. 2024Teaching Large Language Models an Unseen Language on the Flycited by 29
  8. 2020Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representationscited by 21
  9. 2016Continuous multilinguality with language vectorscited by 20
  10. 2024Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problemcited by 17
  11. 2017Predicting Target Language CCG Supertags Improves Neural Machine Translationcited by 15
  12. 2023Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translationcited by 14
  13. 2024Can we teach language models to gloss endangered languages?cited by 14
  14. 2024Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translationcited by 13
  15. 2024Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptionscited by 12
  16. 2024Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Languagecited by 12
  17. 2024Natural Language Processing RELIES on Linguisticscited by 9
  18. 2024LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languagescited by 6
  19. 2019Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translationcited by 5
  20. 2023Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Contextcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 14.

23 papers.

Sort:

By area:

  1. 2025Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchucited by 12
  2. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translationcited by 8
  3. 2025LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMscited by 5
  4. 2025Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Bookscited by 4
  5. 2025Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMscited by 2
  6. 2025Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgmentscited by 2
  7. 2025Prompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languagescited by 1
  8. 2026The Role of Mixed-Language Documents for Multilingual Large Language Model Pretrainingcited by 1
  9. 2026Massively Multilingual Joint Segmentation and Glossingcited by 1
  10. 2026Speaking of Language: Reflections on Metalanguage Research in NLPcited by 1
  11. 2025Testing the Limits of Machine Translation from One Bookcited by 0
  12. 2025Do Large Language Models Grasp The Grammar? Evidence from Grammar-Book-Guided Probing in Luxembourgishcited by 0
11 more
  1. 2026Rashid: A Cipher-Based Framework for Exploring In-Context Language Learningcited by 0
  2. 2026Open Machine Translation for Esperantocited by 0
  3. 2026Evaluating In-Context Translation with Synchronous Context-Free Grammar Transductioncited by 0
  4. 2026Reinforcement Learning Elicits Contextual Learning of Unseen Language Translationcited by 0
  5. 2026LLMs in the Real World: Evaluating "AI" in Emergency Contextscited by 0
  6. 2026A POS Tier Is the Key to Automated Annotation for Low-Resource Language Documentation: Neural Interlinear Glossing for Irabu, a Southern Ryukyuan Languagecited by 0
  7. 2026A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Bookscited by 0
  8. 2026The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Spacecited by 0
  9. 2026Typological Feature Prediction with Large Language Models: An In-Context Learning Approachcited by 0
  10. 2026LLM Agents as Computational Typologistscited by 0
  11. 2026Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Servicescited by 0