arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.02481cs.CL
收藏

面向实际规模的开源大语言模型多语言机器翻译:一项实证研究

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study

Xiaomi Inc.(小米公司)

Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, Bin Wang

AI总结:

本研究探索了小于10B参数的开源大模型的多语言翻译能力,提出PFMS数据混合策略,构建9B的GemmaX2-28模型,在28种语言上超越SOTA模型,媲美Google Translate和GPT-4-turbo。

摘要:

大语言模型(LLMs)展现出持续提升的多语言能力,即便是小规模的开源模型也表现出快速的能力增强。本文系统性地探索了参数少于一百亿的开源LLMs处理多语言机器翻译(MT)任务的能力。我们对六个流行的LLMs进行了全面评估,发现像Gemma2-9B这样的模型展现出令人印象深刻的多语言翻译能力。随后,我们在持续预训练阶段引入了并行优先-单语其次(PFMS)数据混合策略,以进一步增强MT性能,并推出了GemmaX2-28,一个在28种语言上达到顶级多语言翻译性能的9B模型。具体而言,GemmaX2-28持续优于TowerInstruct和XALMA等最先进(SOTA)模型,并与Google Translate和GPT-4-turbo达到竞争性水平。

英文摘要:

Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. In this paper, we systematically explore the abilities of open LLMs with less than ten billion parameters to handle multilingual machine translation (MT) tasks. We conduct comprehensive evaluations on six popular LLMs and find that models like Gemma2-9B exhibit impressive multilingual translation capabilities. We then introduce the Parallel-First Monolingual-Second (PFMS) data mixing strategy in the continual pretraining stage to further enhance the MT performance and present GemmaX2-28, a 9B model achieving top-tier multilingual translation performance across 28 languages. Specifically, GemmaX2-28 consistently outperforms the state-of-the-art (SOTA) models such as TowerInstruct and XALMA and achieves competitive performance with Google Translate and GPT-4-turbo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑