Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 27 Dec 2025.
Builds on
13 of 25 references.
References · 13
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2019TinyBERT: Distilling BERT for Natural Language Understandingcited by 1,153
- 2019Passage Re-ranking with BERTcited by 629
- 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
- 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
- 2024GRAG: Graph Retrieval-Augmented Generationcited by 77
- 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corporacited by 47
- 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
- 2023Lexically-Accelerated Dense Retrievalcited by 7
- 2024Momentum Posterior Regularization for Multi-hop Dense Retrievalcited by 1
1 more
Built on by
Not cited yet.