Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters
This addresses the problem of high-quality multilingual translation for researchers and practitioners, offering an open-source alternative to closed models, though it appears incremental in method.
The authors tackled multilingual translation by introducing Seed-X, a family of open-source LLMs with 7B parameters, achieving performance comparable to leading closed-source models like Gemini-2.5 and GPT-4o across 28 languages and significantly outperforming larger open-source models in automatic metrics and human evaluations.
Multilingual translation stands as a challenging task for large language models (LLMs) to handle intricate language patterns and stilted translations that arise in automated translations. In this paper, we introduce Seed-X, a family of open-source LLMs comprising instruct and reasoning models, pushing the limits of translation capability with 7B parameter size. The base model is pre-trained on a diverse, high-quality dataset encompassing both monolingual and bilingual content across 28 languages, harnessing the full potential of multilingual data. The instruct model is then finetuned to translate by Chain-of-Thought (CoT) reasoning and further enhanced through reinforcement learning (RL) to achieve better generalization across diverse language pairs. Seed-X achieves performance comparable to leading closed-source models, including Gemini-2.5 and GPT-4o, across 28 languages, and significantly outperforms larger open-source models in both automatic metrics and human evaluations. We share the best practices through our optimization process, and make the parameter public available for advancing translation research and applications.