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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cao, Yukun, Gao, Zengyi, Li, Zhiyang, Xie, Xike, Zhou, S. Kevin, Xu, Jianliang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911110628638720
author Cao, Yukun
Gao, Zengyi
Li, Zhiyang
Xie, Xike
Zhou, S. Kevin
Xu, Jianliang
author_facet Cao, Yukun
Gao, Zengyi
Li, Zhiyang
Xie, Xike
Zhou, S. Kevin
Xu, Jianliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05844
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration
Cao, Yukun
Gao, Zengyi
Li, Zhiyang
Xie, Xike
Zhou, S. Kevin
Xu, Jianliang
Artificial Intelligence
Computation and Language
Databases
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.
title LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration
topic Artificial Intelligence
Computation and Language
Databases
url https://arxiv.org/abs/2411.05844