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

Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, Jonathan Larson

2024 | arXiv:2404.16130

Source: https://arxiv.org/abs/2404.16130

Reading scope: abstract-and-metadata

Editorial update: 2026-10-20

Graph communities and summaries support questions about an entire corpus.

## Why this matters

Global synthesis asks more than finding a few relevant passages.

## The proposal

The authors target global questions about document collections. A graph index and community summaries supply material for staged answer synthesis.

## What was inspected

The abstract reports comprehensiveness and diversity improvements for global sensemaking tasks. This does not demonstrate that graphs should replace ordinary retrieval for every query.

## Editorial interpretation

The atlas uses the initial 2024 submission year; the inspected record was revised in 2025. Compare approaches by question type before comparing their outputs.

## Mechanism

Build an entity graph.

Prepare community summaries.

Synthesize partial responses into a final response.

## Limits

Broader coverage does not establish sentence-level truth.

Indexing cost and extraction errors need full-text examination.