Graph Retrieval-Augmented Generation: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Boci, Zhu, Yun, Liu, Yongchao, Bo, Xiaohe, Shi, Haizhou, Hong, Chuntao, Zhang, Yan, Tang, Siliang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909310548705280
author Peng, Boci
Zhu, Yun
Liu, Yongchao
Bo, Xiaohe
Shi, Haizhou
Hong, Chuntao
Zhang, Yan
Tang, Siliang
author_facet Peng, Boci
Zhu, Yun
Liu, Yongchao
Bo, Xiaohe
Shi, Haizhou
Hong, Chuntao
Zhang, Yan
Tang, Siliang
contents Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM outputs, effectively mitigating issues such as ``hallucination'', lack of domain-specific knowledge, and outdated information. However, the complex structure of relationships among different entities in databases presents challenges for RAG systems. In response, GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given the novelty and potential of GraphRAG, a systematic review of current technologies is imperative. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation. We then outline the core technologies and training methods at each stage. Additionally, we examine downstream tasks, application domains, evaluation methodologies, and industrial use cases of GraphRAG. Finally, we explore future research directions to inspire further inquiries and advance progress in the field. In order to track recent progress in this field, we set up a repository at \url{https://github.com/pengboci/GraphRAG-Survey}.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08921
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Retrieval-Augmented Generation: A Survey
Peng, Boci
Zhu, Yun
Liu, Yongchao
Bo, Xiaohe
Shi, Haizhou
Hong, Chuntao
Zhang, Yan
Tang, Siliang
Artificial Intelligence
Computation and Language
Information Retrieval
Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM outputs, effectively mitigating issues such as ``hallucination'', lack of domain-specific knowledge, and outdated information. However, the complex structure of relationships among different entities in databases presents challenges for RAG systems. In response, GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given the novelty and potential of GraphRAG, a systematic review of current technologies is imperative. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation. We then outline the core technologies and training methods at each stage. Additionally, we examine downstream tasks, application domains, evaluation methodologies, and industrial use cases of GraphRAG. Finally, we explore future research directions to inspire further inquiries and advance progress in the field. In order to track recent progress in this field, we set up a repository at \url{https://github.com/pengboci/GraphRAG-Survey}.
title Graph Retrieval-Augmented Generation: A Survey
topic Artificial Intelligence
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2408.08921