LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration

TL;DR

LEGO-GraphRAG introduces a modular framework for graph-based retrieval-augmented generation, enabling detailed analysis, classification, and systematic exploration of GraphRAG techniques for improved reasoning and efficiency.

Contribution

It provides a modular, systematic framework for analyzing, classifying, and creating GraphRAG systems, facilitating empirical studies on large-scale graphs.

Findings

Insights into balancing reasoning quality and computational costs.

Systematic classification of GraphRAG techniques.

Empirical evaluation on real-world graphs.

Abstract

GraphRAG integrates (knowledge) graphs with large language models (LLMs) to improve reasoning accuracy and contextual relevance. Despite its promising applications and strong relevance to multiple research communities, such as databases and natural language processing, GraphRAG currently lacks modular workflow analysis, systematic solution frameworks, and insightful empirical studies. To bridge these gaps, we propose LEGO-GraphRAG, a modular framework that enables: 1) fine-grained decomposition of the GraphRAG workflow, 2) systematic classification of existing techniques and implemented GraphRAG instances, and 3) creation of new GraphRAG instances. Our framework facilitates comprehensive empirical studies of GraphRAG on large-scale real-world graphs and diverse query sets, revealing insights into balancing reasoning quality, runtime efficiency, and token or GPU cost, that are essential for building advanced GraphRAG systems.