KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
This addresses retrieval efficiency and accuracy for complex tasks like multi-hop QA in LLMs, representing an incremental advance in RAG methods.
The paper tackles the challenge of information fragmentation in retrieval-augmented large language models for multi-hop question answering by introducing KG-Retriever, a knowledge graph-based framework with a hierarchical retriever, achieving marked improvements on five public QA datasets.
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.