Highlight

GRAG: Graph Retrieval-Augmented Generation

A method for graph retrieval-augmented generation that tackles networked documents.

Based on

GRAG: Graph Retrieval-Augmented Generation

By Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, Liang Zhao
Read original article →

GRAG addresses limitations of naive RAG by retrieving textual subgraphs and integrating joint textual and topological information into LLMs. It proposes a divide-and-conquer strategy for efficient retrieval and incorporates textual graphs into LLMs through two views.

Experiments demonstrate GRAG's effectiveness in multi-hop reasoning on textual graphs.

Abstract

GRAG addresses limitations of naive RAG by retrieving textual subgraphs and integrating joint textual and topological information into LLMs. It proposes a divide-and-conquer strategy for efficient retrieval and incorporates textual graphs into LLMs through two views. Experiments demonstrate GRAG's effectiveness in multi-hop reasoning on textual graphs.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

graph retrieval-augmented generationtextual subgraphslarge language modelsmulti-hop reasoningtextual graphsKnowledge GraphsLarge Language ModelsRetrieval & RAGSemantic Interoperability
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources