# TULUN: Transparent and Adaptable Low-resource Machine Translation

arXiv: https://arxiv.org/abs/2505.18683 · HTML: https://mlsanity.com/paper/2505.18683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 44 references that are in the map.
- First posted on arXiv 24 May 2025.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [Democratizing Neural Machine Translation with OPUS-MT](https://mlsanity.com/paper/2212.01936/) (2022)
- [Leveraging GPT-4 for Automatic Translation Post-Editing](https://mlsanity.com/paper/2305.14878/) (2023)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations](https://mlsanity.com/paper/2404.07851/) (2024)
- [MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators](https://mlsanity.com/paper/2409.14335/) (2024)
- [PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining](https://mlsanity.com/paper/2108.01887/) (2021)
- [New Trends for Modern Machine Translation with Large Reasoning Models](https://mlsanity.com/paper/2503.10351/) (2025)
- [Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity](https://mlsanity.com/paper/2402.02633/) (2024)
- [Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language](https://mlsanity.com/paper/2404.04809/) (2024)
- [SMOL: Professionally translated parallel data for 115 under-represented languages](https://mlsanity.com/paper/2502.12301/) (2025)
- [Continuous Learning in Neural Machine Translation using Bilingual Dictionaries](https://mlsanity.com/paper/2102.06558/) (2021)
- [Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison](https://mlsanity.com/paper/2404.02835/) (2024)

## Abstract (arXiv)

Machine translation (MT) systems that support low-resource languages often struggle on specialized domains. While researchers have proposed various techniques for domain adaptation, these approaches typically require model fine-tuning, making them impractical for non-technical users and small organizations. To address this gap, we propose Tulun, a versatile solution for terminology-aware translation, combining neural MT with large language model (LLM)-based post-editing guided by existing glossaries and translation memories. Our open-source web-based platform enables users to easily create, edit, and leverage terminology resources, fostering a collaborative human-machine translation process that respects and incorporates domain expertise while increasing MT accuracy. Evaluations show effectiveness in both real-world and benchmark scenarios: on medical and disaster relief translation tasks for Tetun and Bislama, our system achieves improvements of 16.90-22.41 ChrF++ points over baseline MT systems. Across six low-resource languages on the FLORES dataset, Tulun outperforms both standalone MT and LLM approaches, achieving an average improvement of 2.8 ChrF points over NLLB-54B.