HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases

TL;DR

HybGRAG is a novel hybrid retrieval-augmented generation method that effectively combines textual and relational knowledge to improve question answering over semi-structured knowledge bases, outperforming existing approaches.

Contribution

It introduces HybGRAG, a hybrid retrieval system with a retriever bank and critic module, enhancing hybrid question answering by leveraging both textual and relational information.

Findings

HybGRAG surpasses all baselines on HQA benchmarks.

Achieves 51% relative improvement in Hit@1 on STaRK.

Demonstrates effectiveness in integrating textual and relational knowledge.

Abstract

Given a semi-structured knowledge base (SKB), where text documents are interconnected by relations, how can we effectively retrieve relevant information to answer user questions? Retrieval-Augmented Generation (RAG) retrieves documents to assist large language models (LLMs) in question answering; while Graph RAG (GRAG) uses structured knowledge bases as its knowledge source. However, many questions require both textual and relational information from SKB - referred to as "hybrid" questions - which complicates the retrieval process and underscores the need for a hybrid retrieval method that leverages both information. In this paper, through our empirical analysis, we identify key insights that show why existing methods may struggle with hybrid question answering (HQA) over SKB. Based on these insights, we propose HybGRAG for HQA consisting of a retriever bank and a critic module, with the following advantages: (1) Agentic, it automatically refines the output by incorporating feedback from the critic module, (2) Adaptive, it solves hybrid questions requiring both textual and relational information with the retriever bank, (3) Interpretable, it justifies decision making with intuitive refinement path, and (4) Effective, it surpasses all baselines on HQA benchmarks. In experiments on the STaRK benchmark, HybGRAG achieves significant performance gains, with an average relative improvement in Hit@1 of 51%.