用改进的胡蜂滤波器加速树形知识检索，提升生成效率数百倍。
CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter
- 基于树结构与改进胡蜂滤波器，快速定位实体节点。
- 在大量树结构下速度比传统方法快数百倍，生成质量不下降。
- 适合需要高效知识检索的复杂场景，如大规模问答系统。
尽管检索增强生成（RAG）通过引入外部知识库显著提升了生成质量，但在涉及层级结构的Tree-RAG任务中仍面临计算效率瓶颈。本文提出一种基于改进胡蜂滤波器的Tree-RAG加速方法，优化了检索过程中的实体定位，实现显著性能提升。Tree-RAG通过引入层次树结构有效组织实体，而胡蜂滤波器则作为支持快速成员查询和动态更新的高效数据结构。实验结果表明，该方法在保持高生成质量的同时，远快于原始的Tree-RAG；当树的数量较大时，速度提升可达数百倍。代码已开源：https://github.com/TUPYP7180/CFT-RAG-2025。
原文摘要 · Abstract (English)
Although retrieval-augmented generation(RAG) significantly improves generation quality by retrieving external knowledge bases and integrating generated content, it faces computational efficiency bottlenecks, particularly in knowledge retrieval tasks involving hierarchical structures for Tree-RAG. This paper proposes a Tree-RAG acceleration method based on the improved Cuckoo Filter, which optimizes entity localization during the retrieval process to achieve significant performance improvements. Tree-RAG effectively organizes entities through the introduction of a hierarchical tree structure, while the Cuckoo Filter serves as an efficient data structure that supports rapid membership queries and dynamic updates. The experiment results demonstrate that our method is much faster than naive Tree-RAG while maintaining high levels of generative quality. When the number of trees is large, our method is hundreds of times faster than naive Tree-RAG. Our work is available at https://github.com/TUPYP7180/CFT-RAG-2025.
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。