Augmenting Large Language Model Translators via Translation Memories
This work addresses the problem of enhancing translation quality for users of large language models, though it is incremental as it builds on existing prompting methods.
The paper tackled improving large language model translators by using translation memories as prompts, finding that this approach significantly enhances translation results, making them comparable to state-of-the-art neural machine translation systems.
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.