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

2025/02/04 by Menglong Cui, Cui, Menglong, Pengzhi Gao +7 · 11 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques

paper · pdf · doi:10.48550/arxiv.2502.02481

openalex publication_date 2025/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages
• Beyond English: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
• Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation
• Chain-of-Thought Reasoning Improves Context-Aware Translation with Large Language Models
• M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation
• Test-Time Scaling of Reasoning Models for Machine Translation
• OLaPh: Optimal Language Phonemizer
• Evaluating the Impact of Verbal Multiword Expressions on Machine Translation
• Hunyuan-MT Technical Report
• CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
• Beyond the Cloud: Assessing the Benefits and Drawbacks of Local LLM Deployment for Translators

Related

• Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
• How Multilingual Are Large Language Models Fine-Tuned for Translation?
• Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
• Beyond English-Centric Multilingual Machine Translation