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, fail to scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these contrasting methods, we propose a Graph RAG approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed. Our approach uses an LLM to build a graph-based text 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 Graph RAG leads to substantial improvements over a naïve RAG baseline for both the comprehensiveness and diversity of generated answers. An open-source, Python-based implementation of both global and local Graph RAG approaches is forthcoming at this https URL.
Abstract (translated)
利用检索增强生成（RAG）从外部知识源中检索相关信息，使得大型语言模型（LLMs）能够回答从私有和/或之前未见过的文档集合中提出的问题。然而，RAG在指向整个文本语料库的全身问题时失败，例如“数据集的主要主题是什么？”，这是因为这是一个本质上的查询关注度总结（QFS）任务，而不是一个明确的检索任务。同时，之前的前QFS方法也无法扩展到典型RAG系统所索引的文本数量。为了结合这些相互矛盾的方法的优势，我们提出了一个基于图的RAG方法来在私有文本语料库上进行问题回答，该方法能够随着用户问题和要索引的源文本的数量而扩展。我们的方法使用LLM在两个阶段构建一个基于图的文本索引：首先从源文档中提取实体知识图，然后为所有密切相关的实体群组预生成社区摘要。对于一个问题，每个社区摘要用于生成部分回答，然后将所有部分回答再次汇总为对用户的最终回答。在100万词范围内的一类全局理解问题，我们证明了图RAG对于完整性和多样性生成的答案比 naive RAG 基线有了显著的改进。要在该https URL上找到一个开源的、基于全局和局部 Graph RAG方法的Python实现。
URL
https://arxiv.org/abs/2404.16130
