From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Researchers have introduced GraphRAG, a graph-based approach to retrieval-augmented generation that enables large language models to answer global, query-focused summarization questions over entire text corpora. The method builds an entity knowledge graph from source documents and generates community summaries for groups of related entities, then synthesizes partial responses into a final answer. In tests on datasets of up to 1 million tokens, GraphRAG substantially outperformed conventional RAG baselines in both the comprehensiveness and diversity of generated answers.

Computer Science Computation and Language Submitted on 24 Apr 2024 v1 https://arxiv.org/abs/2404.16130v1 , last revised 19 Feb 2025 this version, v2 Title:From Local to Global: A Graph RAG Approach to Query-Focused Summarization View PDF /pdf/2404.16130 HTML experimental https://arxiv.org/html/2404.16130v2 Abstract:The use of retrieval-augmented generation RAG to retrieve relevant information from an external knowledge source enables large language models LLMs to answer questions over private and/or previously unseen document collections. However, RAG fails on global questions directed at an entire text corpus, such as "What are the main themes in the dataset?", since this is inherently a query-focused summarization QFS task, rather than an explicit retrieval task. Prior QFS methods, meanwhile, do not scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these contrasting methods, we propose GraphRAG, a graph-based approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text. Our approach uses an LLM to build a graph index in two stages: first, to derive an entity knowledge graph from the source documents, then to pregenerate community summaries for all groups of closely related entities. Given a question, each community summary is used to generate a partial response, before all partial responses are again summarized in a final response to the user. For a class of global sensemaking questions over datasets in the 1 million token range, we show that GraphRAG leads to substantial improvements over a conventional RAG baseline for both the comprehensiveness and diversity of generated answers. Submission history From: Darren Edge view email /show-email/99103aef/2404.16130 Wed, 24 Apr 2024 18:38:11 UTC 6,306 KB v1 /abs/2404.16130v1 v2 Wed, 19 Feb 2025 10:49:41 UTC 6,322 KB Current browse context: cs.CL References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface Papers with Code What is Papers with Code? https://paperswithcode.com/ ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .