单语还是多语指令微调：哪种方法能打造更优的Alpaca
Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca
AI总结：
该研究针对多语言场景下的大语言模型指令微调策略展开实证分析，对比单语与多语微调效果，发现多语微调性价比更高，可为扩展模型语言支持提供参考。
摘要：
基础大语言模型（LLM）可通过指令微调执行开放域问答，支撑聊天助手等应用。尽管此类工作通常以单语言开展，我们针对多语言场景的高性价比策略展开实证分析。本研究采用Alpaca数据集及其机器翻译结果构建多语言数据，再通过低秩适配或全参数训练对LLM进行微调。在受控计算预算下的对比表明，多语微调的效果与为每种语言单独微调模型相当甚至更优。此外，使用下采样数据的多语微调性能相当且鲁棒性更强。我们的研究结果可为通过指令微调扩展语言支持提供指导。
英文摘要：
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.
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。
