This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
Meta AI 的研究人员引入了一种叫做[检索增强生成(Retrieval Augmented Generation,RAG)](https://ai.facebook.com/blog/retrieval-augmented-generation-streamlining-the-creation-of-intelligent-natural-language-processing-models/)的方法来完成这类知识密集型的任务。RAG 把一个信息检索组件和文本生成模型结合在一起。RAG 可以微调,其内部知识的修改方式很高效,不需要对整个模型进行重新训练。