BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages

TL;DR

BigTranslate enhances open-source LLaMA models with multilingual translation capabilities across over 100 languages, achieving performance comparable to commercial systems like ChatGPT and Google Translate.

Contribution

It introduces a novel training pipeline that significantly expands LLaMA's multilingual translation abilities beyond its original 20 languages.

Findings

Performs comparably with ChatGPT and Google Translate in many languages

Outperforms ChatGPT in 8 language pairs

Successfully extends LLaMA to over 100 languages

Abstract

Large language models (LLMs) demonstrate promising translation performance among various natural languages. However, many LLMs especially the open-sourced ones, such as BLOOM and LLaMA, are English-dominant and support only dozens of natural languages, making the potential of LLMs on language translation less explored. In this work, we present BigTranslate which adapts LLaMA that covers only 20 languages and enhances it with multilingual translation capability on more than 100 languages. BigTranslate is built upon LLaMA-13B and it is optimized in three steps. First, we continue training LLaMA with massive Chinese monolingual data. Second, we continue training the model with a large-scale parallel dataset that covers 102 natural languages. Third, we instruct-tune the foundation model with multilingual translation instructions, leading to our BigTranslate model. The preliminary experiments on multilingual translation show that BigTranslate performs comparably with ChatGPT and Google Translate in many languages and even outperforms ChatGPT in 8 language pairs. We release the BigTranslate model and hope it can advance the research progress.