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

arXiv: https://arxiv.org/abs/2410.18702 · HTML: https://mlsanity.com/paper/2410.18702/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [The unreasonable effectiveness of few-shot learning for machine translation](https://mlsanity.com/paper/2302.01398/) (2023)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Unbabel's Participation in the WMT20 Metrics Shared Task](https://mlsanity.com/paper/2010.15535/) (2020)
- [The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation](https://mlsanity.com/paper/2110.03036/) (2021)
- [Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions](https://mlsanity.com/paper/2401.08429/) (2024)
- [Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions](https://mlsanity.com/paper/2402.18025/) (2024)
- [Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts](https://mlsanity.com/paper/2209.11409/) (2022)
- [Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation](https://mlsanity.com/paper/1911.02709/) (2019)
- [Syntactically Guided Neural Machine Translation](https://mlsanity.com/paper/1605.04569/) (2016)

## Built on by (most cited first, 5 of 5)

- [LingGym: How Far Are LLMs from Thinking Like Field Linguists?](https://mlsanity.com/paper/2511.00343/) (2025)
- [Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books](https://mlsanity.com/paper/2506.01796/) (2025)
- [Massively Multilingual Joint Segmentation and Glossing](https://mlsanity.com/paper/2601.10925/) (2026)
- [Testing the Limits of Machine Translation from One Book](https://mlsanity.com/paper/2508.06665/) (2025)
- [Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning](https://mlsanity.com/paper/2603.22497/) (2026)

## 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.