| title | Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay |
|---|---|
| authors | Joanito Agili Lopo, Yunita Sari, Guntur Budi Herwanto |
| date | 2026-06-10 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.11786 |
| affiliation | haim |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages. To address this limitation, we propose an approach for fine-tuning LLMs on a low-resource language, Kupang Malay. Our approach involves designing a set of instructions by leveraging explicit lexical and semantic features from a bilingual dictionary, and introducing Continual Instruction Tuning (CIT), a training paradigm that enables iterative instruction-based training. Experimental results demonstrate that our model, named Lius, yields notable improvements over standard instruction-tuned models by outperforming 4-6 points, and surpassing both Neural Machine Translation (NMT) and Multilingual LLM models by 10-13 points on several evaluation metrics. These findings highlight the potential of our approach to mitigate the reliance on large-scale parallel data in low-resource language translation. |
cite
@misc{lopo2026lius,
title={Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay},
author={Joanito Agili Lopo and Yunita Sari and Guntur Budi Herwanto},
year={2026},
eprint={2606.11786},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.11786}
}