无需GPU和昂贵计算，用简单方法实现高效多跳问答检索。
Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA
- 用命名实体识别构建共现图，替代复杂LLM生成
- 线性时间处理，召回率仅下降28%，保持高效
- 适合资源有限但需多跳推理的场景
GraphRAG系统通过建模结构提升多跳检索性能，但多数依赖昂贵的LLM图构建和高功耗推理。本文提出SPRIG（基于种子传播的图检索），一个纯CPU、线性时间、无令牌开销的GraphRAG流程：以轻量级命名实体识别驱动的共现图替代LLM建图，采用个性化PageRank（PPR）进行检索，实现28%的性能下降，同时召回率@10变化微乎其微。结果揭示了在何种条件下，低成本图检索可有效提升多跳问答，并说明在某些场景下，简单的词法融合（RRF）已足够。该研究为降低GraphRAG门槛、实现真正普及提供了可行路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。