Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning.

翻译：基础大型语言模型可以通过指令微调来执行开放域问答，从而支持聊天助手等应用。虽然这类工作通常以单一语言进行，但我们通过实证分析探索了多语言场景下的成本效益策略。本研究采用Alpaca数据集及其机器翻译版本构建多语言数据，并通过低秩适应或全参数训练对LLM进行微调。在受控计算预算下，比较结果显示多语言微调的效果优于或等同于为每种语言单独微调模型。此外，采用下采样数据的多语言微调不仅性能相当，而且鲁棒性更强。我们的发现为通过指令微调扩展语言支持提供了指导。