让翻译增强模型同时具备强推理能力，打破性能瓶颈
LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoning
- 仅对平行语料做层选择性微调，提升多语言翻译能力
- 低资源语言翻译达40+ xComet，多任务平均提升1+点
- 适合需要多语言推理的场景，开源可复用
通用大语言模型在推理方面表现优异，但经过翻译增强的模型往往在推理任务上表现不佳。为此，我们提出一种新的翻译增强方法：从指令模型出发，仅对平行数据进行层选择性微调。基于该流程，我们推出了Qwen3-XPlus系列模型，在高、低资源语言中均显著提升翻译性能，低资源语言（如斯瓦希里语）达到15+ spBLEU和40+ xComet。有趣的是，仅使用小规模平行数据训练，Qwen3-XPlus在7个跨语言任务上平均提升1+点，同时在15个主流推理数据集上的表现与Qwen3指令模型相当。该工作为多语言增强提供了高效路径，大幅降低复杂度并提升语言可及性。代码与模型已公开。
原文摘要 · Abstract (English)
General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies layer-selective tuning only on parallel data. Following this pipeline, we introduce the Qwen3-XPlus models, which demonstrate significant improvements in translation performance across both high- and lowresource languages, achieving 15+ spBLEU and 40+ xComet in low-resource languages, like Swahili. Interestingly, training only with small parallel datasets, Qwen3-XPlus achieves an average improvement of 1+ points on 7 multilingual tasks while maintaining proficiency comparable to the Qwen3 instruct model in 15 popular reasoning datasets. This work offers a promising approach to multilingual enhancement, significantly reducing complexity and enhancing accessibility for a wider range of languages. The code and model are publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。