Enhancing Large Language Models'Machine Translation via Dynamic Focus Anchoring

TL;DR

This paper introduces a method to improve large language models' machine translation accuracy by dynamically focusing on context-sensitive units, enhancing translation quality without additional training.

Contribution

The proposed approach identifies and incorporates context-sensitive units into LLMs dynamically, improving translation accuracy and robustness across multiple language pairs without extra training.

Findings

Achieved competitive performance on MT benchmarks.

Effective across both similar and distant language pairs.

Requires no additional model training or significant resources.

Abstract

Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT). However, persistent challenges remain in addressing context-sensitive units (CSUs), such as polysemous words. These CSUs not only affect the local translation accuracy of LLMs, but also affect LLMs' understanding capability for sentences and tasks, and even lead to translation failure. To address this problem, we propose a simple but effective method to enhance LLMs' MT capabilities by acquiring CSUs and applying semantic focus. Specifically, we dynamically analyze and identify translation challenges, then incorporate them into LLMs in a structured manner to mitigate mistranslations or misunderstandings of CSUs caused by information flattening. Efficiently activate LLMs to identify and apply relevant knowledge from its vast data pool in this way, ensuring more accurate translations for translating difficult terms. On a benchmark dataset of MT, our proposed method achieved competitive performance compared to multiple existing open-sourced MT baseline models. It demonstrates effectiveness and robustness across multiple language pairs, including both similar language pairs and distant language pairs. Notably, the proposed method requires no additional model training and enhances LLMs' performance across multiple NLP tasks with minimal resource consumption.