# Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG

arXiv: https://arxiv.org/abs/2601.09982 · HTML: https://mlsanity.com/paper/2601.09982/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 15 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation](https://mlsanity.com/paper/2005.03642/) (2020)
- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [Domain Robustness in Neural Machine Translation](https://mlsanity.com/paper/1911.03109/) (2019)
- [Domain Adaptation of Neural Machine Translation by Lexicon Induction](https://mlsanity.com/paper/1906.00376/) (2019)
- [Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity](https://mlsanity.com/paper/2402.02633/) (2024)
- [Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation](https://mlsanity.com/paper/2503.04554/) (2025)
- [SMOL: Professionally translated parallel data for 115 under-represented languages](https://mlsanity.com/paper/2502.12301/) (2025)
- [It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs](https://mlsanity.com/paper/2508.19089/) (2025)
- [Limitations of Religious Data and the Importance of the Target Domain: Towards Machine Translation for Guinea-Bissau Creole](https://mlsanity.com/paper/2504.02674/) (2025)

## Abstract (arXiv)

Neural Machine Translation (NMT) models for low-resource languages suffer significant performance degradation under domain shift. We quantify this challenge using Dhao, an indigenous language of Eastern Indonesia with no digital footprint beyond the New Testament (NT). When applied to the unseen Old Testament (OT), a standard NMT model fine-tuned on the NT drops from an in-domain score of 36.17 chrF++ to 27.11 chrF++. To recover this loss, we introduce a hybrid framework where a fine-tuned NMT model generates an initial draft, which is then refined by a Large Language Model (LLM) using Retrieval-Augmented Generation (RAG). The final system achieves 35.21 chrF++ (+8.10 recovery), effectively matching the original in-domain quality. Our analysis reveals that this performance is driven primarily by the number of retrieved examples rather than the choice of retrieval algorithm. Qualitative analysis confirms the LLM acts as a robust "safety net," repairing severe failures in zero-shot domains.