Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA
Qizhi Wang

TL;DR
This paper introduces SPRIG, a CPU-only, efficient GraphRAG pipeline that replaces costly LLM-based graph construction with lightweight methods, enabling more accessible multi-hop question answering without expensive hardware.
Contribution
SPRIG offers a novel, linear-time, CPU-only GraphRAG approach using lightweight NER-driven graphs and PPR, reducing costs and hardware requirements for multi-hop QA.
Findings
Achieves 28% improvement with negligible Recall@10 change
Characterizes when CPU-friendly retrieval enhances multi-hop recall
Outlines a path for democratizing GraphRAG technology
Abstract
GraphRAG systems improve multi-hop retrieval by modeling structure, but many approaches rely on expensive LLM-based graph construction and GPU-heavy inference. We present SPRIG (Seeded Propagation for Retrieval In Graphs), a CPU-only, linear-time, token-free GraphRAG pipeline that replaces LLM graph building with lightweight NER-driven co-occurrence graphs and uses Personalized PageRank (PPR) for 28% with negligible Recall@10 changes. The results characterize when CPU-friendly graph retrieval helps multi-hop recall and when strong lexical hybrids (RRF) are sufficient, outlining a realistic path to democratizing GraphRAG without token costs or GPU requirements.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGraph Theory and Algorithms · Advanced Graph Neural Networks · Information Retrieval and Search Behavior
