mlsanityData to 7 Oct 2026

GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning

arXiv 2410.18702 ↗First posted 24 Oct 2024cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations for source sentences. GrammaMT proposes three prompting strategies: gloss-shot, chain-gloss and model-gloss. All are training-free, requiring only a few examples that involve minimal effort to collect, and making them well-suited for low-resource setups. Experiments show that GrammaMT enhances translation performance on open-source instruction-tuned LLMs for various low- to high-resource languages across three benchmarks: (1) the largest IGT corpus, (2) the challenging 2023 SIGMORPHON Shared Task data over endangered languages, and (3) even in an out-of-domain setting with FLORES. Moreover, ablation studies reveal that leveraging gloss resources could substantially boost MT performance (by over 17 BLEU points) if LLMs accurately generate or access input sentence glosses.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 24 Oct 2024.

Builds on

23 of 39 references.

References · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2024Self-Rewarding Language Modelscited by 654
  6. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  7. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 504
  8. 2017Word Translation Without Parallel Datacited by 480
  9. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
  10. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 292
  11. 2023xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detectioncited by 260
  12. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
11 more
  1. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
  2. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  3. 2023Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translationcited by 74
  4. 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 74
  5. 2020Unbabel's Participation in the WMT20 Metrics Shared Taskcited by 56
  6. 2021The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translationcited by 46
  7. 2024Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directionscited by 12
  8. 2024Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptionscited by 12
  9. 2022Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Promptscited by 7
  10. 2019Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translationcited by 5
  11. 2016Syntactically Guided Neural Machine Translationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025LingGym: How Far Are LLMs from Thinking Like Field Linguists?cited by 6
  2. 2025Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Bookscited by 4
  3. 2026Massively Multilingual Joint Segmentation and Glossingcited by 1
  4. 2025Testing the Limits of Machine Translation from One Bookcited by 0
  5. 2026Rashid: A Cipher-Based Framework for Exploring In-Context Language Learningcited by 0