Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large language models (LLMs) with TMs and making them better translators. We find that the ability of LLMs to ``understand'' prompts is indeed helpful for making better use of TMs. Experiments show that the results of a pre-trained LLM translator can be greatly improved by using high-quality TM-based prompts. These results are even comparable to those of the state-of-the-art NMT systems which have access to large-scale in-domain bilingual data and are well tuned on the downstream tasks.
@article{arxiv.2305.17367,
title = {Augmenting Large Language Model Translators via Translation Memories},
author = {Yongyu Mu and Abudurexiti Reheman and Zhiquan Cao and Yuchun Fan and Bei Li and Yinqiao Li and Tong Xiao and Chunliang Zhang and Jingbo Zhu},
journal= {arXiv preprint arXiv:2305.17367},
year = {2023}
}