# Millions of $\\text{GeAR}$-s: Extending GraphRAG to Millions of Documents

Source: [Millions of $\\text{GeAR}$-s: Extending GraphRAG to Millions of Documents](<https://www.sota2.com/research/paper/68fa7a271e209131cea815f7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:13:22.731Z

Authors: Zhili Shen, Chenxin Diao, Pascual Merita, Pavlos Vougiouklis, Jeff Z. Pan

Published: 2025-07-23T10:54:24.000Z

## Abstract

Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: $\\text{GeAR}$ and explore its performance and limitations on the SIGIR 2025 LiveRAG Challenge.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.17399>)

[PDF](<https://arxiv.org/pdf/2507.17399.pdf>)
