KG-Retriever：面向检索增强大语言模型的高效知识索引
KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
AI总结：
本文提出KG-Retriever框架，通过知识图谱层与协作文档层构成的分层索引图增强文档连通性，缓解多跳问答中的信息碎片化问题，并在五个QA数据集上验证了其检索效果与效率。
摘要：
具有检索增强生成的大语言模型在复杂检索任务中面临关键挑战，例如多跳问答，这要求模型跨多个文档进行导航，并基于碎片化信息生成全面回答。为应对这一挑战，我们提出了一种新颖的基于知识图谱的RAG框架，并配备分层知识检索器，称为KG-Retriever。KG-Retriever中的检索索引构建在一个分层索引图上，该图由知识图谱层和协作文档层组成。图结构的关联特性被充分利用，以增强文档内和文档间的连通性，从而从根本上缓解信息碎片化问题，同时提高大语言模型跨文档检索的效率。借助来自相邻文档的粗粒度协作信息以及来自知识图谱的简洁信息，KG-Retriever在五个公开问答数据集上取得了显著改进，展示了我们所提出的RAG框架的有效性和高效性。
英文摘要：
Large language models with retrieval-augmented generation encounter a pivotal challenge in intricate retrieval tasks, e.g., multi-hop question answering, which requires the model to navigate across multiple documents and generate comprehensive responses based on fragmented information. To tackle this challenge, we introduce a novel Knowledge Graph-based RAG framework with a hierarchical knowledge retriever, termed KG-Retriever. The retrieval indexing in KG-Retriever is constructed on a hierarchical index graph that consists of a knowledge graph layer and a collaborative document layer. The associative nature of graph structures is fully utilized to strengthen intra-document and inter-document connectivity, thereby fundamentally alleviating the information fragmentation problem and meanwhile improving the retrieval efficiency in cross-document retrieval of LLMs. With the coarse-grained collaborative information from neighboring documents and concise information from the knowledge graph, KG-Retriever achieves marked improvements on five public QA datasets, showing the effectiveness and efficiency of our proposed RAG framework.
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。
