Using large language models, this paper presents techniques to improve extremely low-resourced indigenous language translations. Our approaches are grounded in the use of (1) the presence of a datastore consisting of a limited number of parallel translation examples, (2) the inherent capabilities of LLMs like GPT-3.5, and (3) a word-level translation dictionary. We harness the potential of LLMs and in-context learning techniques in such a setting for using LLMs as universal translators for extremely low-resourced languages. Our methodology hinges on utilizing LLMs as language compilers for selected language pairs, hypothesizing that they could internalize syntactic structures to facilitate accurate translation. We introduce three techniques: KNNPrompting with Retrieved Prompting Context, Chain-of-Thought Prompting and Learningfrom-Mistakes Prompting, with the last method addressing past errors. The evaluation results suggest that, even with limited corpora, LLMs can effectively translate extremely low-resource languages when paired with proper prompting.
@article{arxiv.2407.13343,
title = {Learning-From-Mistakes Prompting for Indigenous Language Translation},
author = {You-Cheng Liao and Chen-Jui Yu and Chi-Yi Lin and He-Feng Yun and Yen-Hsiang Wang and Hsiao-Min Li and Yao-Chung Fan},
journal= {arXiv preprint arXiv:2407.13343},
year = {2024}
}