We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language model finetuned on a small amount of seed data, and a given web corpus. The seed model is used to construct training examples by generating instruction prompts for web documents (self-augmentation), and then selecting high quality examples from among these candidates (self-curation). This data is then used to finetune a stronger model. Finetuning LLaMa on two iterations of our approach yields a model that outperforms all other LLaMa-based models on the Alpaca leaderboard not relying on distillation data, demonstrating highly effective self-alignment.

翻译：我们提出了一种可扩展的方法，通过自动对人工撰写的文本标注相应指令，来构建高质量的指令跟随语言模型。该方法名为"指令反向翻译"，其流程包括：首先使用少量种子数据微调语言模型，并给定网络语料库；随后，该种子模型通过为网络文档生成指令提示（自我增强）来构建训练样本，再从中筛选高质量示例（自我筛选）；最终利用这些数据微调出更强的模型。通过两轮该方法微调LLaMA模型，得到的模型在Alpaca排行榜上超越了所有不依赖蒸馏数据的其他LLaMA模型，展现了高效的自我对齐能力。