Summary of From Local to Global: a Graph Rag Approach to Query-focused Summarization, by Darren Edge et al.
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
by Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, Jonathan Larson
First submitted to arxiv on: 24 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents GraphRAG, a novel approach to question answering over private text corpora. By combining retrieval-augmented generation (RAG) with graph-based methods, GraphRAG scales to large quantities of text and can answer global sensemaking questions that RAG alone cannot handle. The authors use a language model to build an entity knowledge graph from source documents, pregenerate community summaries for related entities, and then generate partial responses based on these summaries. This approach leads to substantial improvements in the comprehensiveness and diversity of generated answers over a conventional RAG baseline. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GraphRAG is a new way to answer questions using large language models. It’s like a super smart librarian who can find answers to big questions by looking at lots of books. The author’s approach uses two steps: first, they make a special graph that shows how different pieces of information are related. Then, when someone asks a question, the system looks for relevant parts of the graph and puts together an answer. This helps make sure the answer is complete and makes sense. |
Keywords
» Artificial intelligence » Knowledge graph » Language model » Question answering » Rag » Retrieval augmented generation
