Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910034657542144 |
|---|---|
| author | Wang, Qizhi |
| author_facet | Wang, Qizhi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA Wang, Qizhi Information Retrieval Artificial Intelligence Computation and Language 68T50 (Primary) 68P20, 68T05 (Secondary) H.3.3; I.2.7; I.2.6 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. |
| title | Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA |
| topic | Information Retrieval Artificial Intelligence Computation and Language 68T50 (Primary) 68P20, 68T05 (Secondary) H.3.3; I.2.7; I.2.6 |
| url | https://arxiv.org/abs/2602.23372 |