# Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books

arXiv: https://arxiv.org/abs/2506.01796 · HTML: https://mlsanity.com/paper/2506.01796/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting](https://mlsanity.com/paper/2212.09535/) (2022)
- [Do Multilingual Language Models Think Better in English?](https://mlsanity.com/paper/2308.01223/) (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)
- [Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?](https://mlsanity.com/paper/2409.19151/) (2024)
- [Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs](https://mlsanity.com/paper/2401.10065/) (2024)
- [Shortcomings of LLMs for Low-Resource Translation: Retrieval and Understanding are Both the Problem](https://mlsanity.com/paper/2406.15625/) (2024)
- [Can we teach language models to gloss endangered languages?](https://mlsanity.com/paper/2406.18895/) (2024)
- [GlossLM: A Massively Multilingual Corpus and Pretrained Model for Interlinear Glossed Text](https://mlsanity.com/paper/2403.06399/) (2024)
- [Back to School: Translation Using Grammar Books](https://mlsanity.com/paper/2410.15263/) (2024)
- [Leveraging Code to Improve In-context Learning for Semantic Parsing](https://mlsanity.com/paper/2311.09519/) (2023)
- [Eliciting Better Multilingual Structured Reasoning from LLMs through Code](https://mlsanity.com/paper/2403.02567/) (2024)
- [GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning](https://mlsanity.com/paper/2410.18702/) (2024)

## Built on by (most cited first, 4 of 4)

- [Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation](https://mlsanity.com/paper/2604.18758/) (2026)
- [Rashid: A Cipher-Based Framework for Exploring In-Context Language Learning](https://mlsanity.com/paper/2603.22497/) (2026)
- [Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion](https://mlsanity.com/paper/2604.18106/) (2026)
- [A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books](https://mlsanity.com/paper/2607.22376/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have shown promise in translating extremely low-resource languages using resources like dictionaries, the effectiveness of grammar books remains debated. This paper investigates the role of grammar books in translating extremely low-resource languages by decomposing it into two key steps: grammar rule retrieval and application. To facilitate the study, we introduce ZhuangRules, a modularized dataset of grammar rules and their corresponding test sentences. Our analysis reveals that rule retrieval constitutes a primary bottleneck in grammar-based translation. Moreover, although LLMs can apply simple rules for translation when explicitly provided, they encounter difficulties in handling more complex rules. To address these challenges, we propose representing grammar rules as code functions, considering their similarities in structure and the benefit of code in facilitating LLM reasoning. Our experiments show that using code rules significantly boosts both rule retrieval and application, ultimately resulting in a 13.1% BLEU improvement in translation.