用抽象树提升大模型生成质量，检索速度更快。
Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm
- 构建抽象树结构，通过语义桥接实现多层级精准检索。
- 在所有指标上均提升生成质量，检索速度最快快1.9倍。
- 适合需要高效高质生成的对话系统与知识问答场景。
作为提升大语言模型生成质量的重要范式，检索增强生成（RAG）面临检索准确率和计算效率两大挑战。本文提出一种新型RAG框架Bridge-RAG。为解决准确率问题，引入抽象概念，桥接查询实体与文档块，实现稳健的语义理解；将抽象组织成树形结构，并设计多级检索策略，确保充分上下文信息的纳入。尽管该分层结构显著提升答案质量，但遍历树以定位包含查询实体的抽象仍带来额外检索开销。为此，进一步集成布谷鸟过滤器（Cuckoo Filter）形成CFT-RAG，实现O(1)实体查找，天然契合框架中的实体-抽象路径。大量实验表明，Bridge-RAG在所有指标上均实现一致的准确率提升，且相比结构化RAG基线最高达1.9倍的检索加速。
原文摘要 · Abstract (English)
As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the two challenges regarding retrieval accuracy and computational efficiency. This paper presents a novel RAG framework called Bridge-RAG. To overcome the accuracy challenge, we introduce the concept of abstract to bridge query entities and document chunks, providing robust semantic understanding. We organize the abstracts into a tree structure and design a multi-level retrieval strategy to ensure the inclusion of sufficient contextual information. While this hierarchical organization substantially improves answer quality, traversing the tree to locate the abstracts that contain a query entity inevitably introduces additional retrieval overhead. To restore retrieval efficiency, we further integrate the Cuckoo Filter in CFT-RAG, which provides O(1) entity lookup and naturally fits the entity-to-abstract pathway of our framework. Extensive experiments show that Bridge-RAG achieves consistent accuracy improvements across all metrics and up to $1.9\times$ faster retrieval compared to structured RAG baselines.
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。