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

• URL: http://arxiv.org/abs/2404.16130v1
• Date: Wed, 24 Apr 2024 18:38:11 GMT
• Title: From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Authors: Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Jonathan Larson,
• Abstract summary: We propose a Graph RAG approach to question answering over private text corpora. Our approach uses an entity knowledge graph from the source documents, then to pregenerate community summaries for all groups of closely-related entities. 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 na"ive RAG baseline.
• Score: 3.9676927113698626
• License: http://creativecommons.org/licenses/by/4.0/
• 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 na\"ive 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 https://aka.ms/graphrag.

Related papers

• RAG-ConfusionQA: A Benchmark for Evaluating LLMs on Confusing Questions [52.33835101586687]
  Conversational AI agents use Retrieval Augmented Generation (RAG) to provide verifiable document-grounded responses to user inquiries. This paper presents a novel synthetic data generation method to efficiently create a diverse set of context-grounded confusing questions from a given document corpus.
  arXiv  Detail & Related papers  (2024-10-18T16:11:29Z)
• Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation [65.16137964758612]
  We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text.
  arXiv  Detail & Related papers  (2024-05-31T20:15:10Z)
• Don't Forget to Connect! Improving RAG with Graph-based Reranking [26.433218248189867]
  We introduce G-RAG, a reranker based on graph neural networks (GNNs) between the retriever and reader in RAG. Our method combines both connections between documents and semantic information (via Abstract Representation Meaning graphs) to provide a context-informed ranker for RAG. G-RAG outperforms state-of-the-art approaches while having smaller computational footprint.
  arXiv  Detail & Related papers  (2024-05-28T17:56:46Z)
• TANQ: An open domain dataset of table answered questions [15.323690523538572]
  TANQ is the first open domain question answering dataset where the answers require building tables from information across multiple sources. We release the full source attribution for every cell in the resulting table and benchmark state-of-the-art language models in open, oracle, and closed book setups. Our best-performing baseline, GPT4 reaches an overall F1 score of 29.1, lagging behind human performance by 19.7 points.
  arXiv  Detail & Related papers  (2024-05-13T14:07:20Z)
• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering [61.93058781222079]
  We develop a flexible question-answering framework targeting real-world textual graphs. We introduce the first retrieval-augmented generation (RAG) approach for general textual graphs. G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem.
  arXiv  Detail & Related papers  (2024-02-12T13:13:04Z)
• RAG-Fusion: a New Take on Retrieval-Augmented Generation [0.0]
  Infineon has identified a need for engineers, account managers, and customers to rapidly obtain product information. This research marks significant progress in artificial intelligence (AI) and natural language processing (NLP) applications.
  arXiv  Detail & Related papers  (2024-01-31T22:06:07Z)
• LMGQS: A Large-scale Dataset for Query-focused Summarization [77.6179359525065]
  We convert four generic summarization benchmarks into a new QFS benchmark dataset, LMGQS. We establish baselines with state-of-the-art summarization models. We achieve state-of-the-art zero-shot and supervised performance on multiple existing QFS benchmarks.
  arXiv  Detail & Related papers  (2023-05-22T14:53:45Z)
• Open Domain Question Answering over Virtual Documents: A Unified Approach for Data and Text [62.489652395307914]
  We use the data-to-text method as a means for encoding structured knowledge for knowledge-intensive applications, i.e. open-domain question answering (QA) Specifically, we propose a verbalizer-retriever-reader framework for open-domain QA over data and text where verbalized tables from Wikipedia and triples from Wikidata are used as augmented knowledge sources. We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over text-only baselines.
  arXiv  Detail & Related papers  (2021-10-16T00:11:21Z)
• UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text [20.1784368017206]
  Question answering over RDF data like knowledge graphs has been greatly advanced. IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora.
  arXiv  Detail & Related papers  (2021-08-19T10:50:52Z)
• Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks [4.550927535779247]
  This paper addresses the task of (complex) conversational question answering over a knowledge graph. We propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks) We show that LASAGNE improves the F1-score on eight out of ten question types.
  arXiv  Detail & Related papers  (2021-04-04T09:21:50Z)
• Semantic Graphs for Generating Deep Questions [98.5161888878238]
  We propose a novel framework which first constructs a semantic-level graph for the input document and then encodes the semantic graph by introducing an attention-based GGNN (Att-GGNN) On the HotpotQA deep-question centric dataset, our model greatly improves performance over questions requiring reasoning over multiple facts, leading to state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-04-27T10:52:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.