Instruction tuning is essential for large language models (LLMs) to become interactive. While many instruction tuning datasets exist in English, there is a noticeable lack in other languages. Also, their effectiveness has not been well verified in non-English languages. We construct a Japanese instruction dataset by expanding and filtering existing datasets and apply the dataset to a Japanese pre-trained base model. We performed Low-Rank Adaptation (LoRA) tuning on both Japanese and English existing models using our instruction dataset. We evaluated these models from both quantitative and qualitative perspectives. As a result, the effectiveness of Japanese instruction datasets is confirmed. The results also indicate that even with relatively small LLMs, performances in downstream tasks would be improved through instruction tuning. Our instruction dataset, tuned models, and implementation are publicly available online.

翻译：指令调优对于使大语言模型具备交互能力至关重要。尽管英语中存在大量指令调优数据集，但其他语言中明显缺乏此类资源。此外，这些数据集在非英语语言中的有效性尚未得到充分验证。我们通过扩展和筛选现有数据集构建了一个日语指令数据集，并将其应用于预训练的日语基础模型。我们使用该指令数据集对日语和英语现有模型进行了低秩适配（LoRA）调优，并从定量和定性两个角度评估了这些模型。结果表明，日语指令数据集的有效性得到了证实。同时，即便在规模相对较小的大语言模型上，指令调优也能提升下游任务的性能。我们的指令数据集、调优模型及实现代码均已公开在线发布。