Retrieval-Augmented Generation (RAG) has significantly demonstrated the performance of Large Language Models (LLMs) in the knowledge-intensive tasks, such as Question-Answering (QA). RAG expands the query context by incorporating external knowledge bases to enhance the response accuracy. However, it would be inefficient to access LLMs multiple times for each query and unreliable to retrieve all the relevant documents by a single query. We find that even though there is low relevance between some critical documents and query, it is possible to retrieve the remaining documents by combining parts of the documents with the query. To mine the relevance, a two-stage retrieval framework called Dynamic-Relevant Retrieval-Augmented Generation (DR-RAG) is proposed to improve document retrieval recall and the accuracy of answers while maintaining efficiency. Also, a small classifier is applied to two different selection strategies to determine the contribution of the retrieved documents to answering the query and retrieve the relatively relevant documents. Meanwhile, DR-RAG call the LLMs only once, which significantly improves the efficiency of the experiment. The experimental results on multi-hop QA datasets show that DR-RAG can significantly improve the accuracy of the answers and achieve new progress in QA systems.

通过将外部知识库融入到Retrieval-Augmented Generation (RAG)中，提出了一种名为Dynamic-Relevant Retrieval-Augmented Generation （DR-RAG）的两阶段检索框架，用于改善文档检索的召回率和答案的准确性，同时保持高效性，通过对检索到的文档的贡献进行分类确定相对相关的文档，实验证明DR-RAG能显著提高答案的准确性，并在QA系统方面取得新的进展。

DR-RAG: 将动态文档相关性应用于检索增强问答生成