arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.20926cs.AI
收藏

HELP: 图形节点扩展与逻辑路径引导的证据定位用于准确且高效的图RAG

HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG

Shanghai Jiao Tong University, China(上海交通大学)

Yuqi Huang, Ning Liao, Kai Yang, Anning Hu, Shengchao Hu, Xiaoxing Wang, Junchi Yan

AI总结:

HELP通过HyperNode扩展和逻辑路径引导的证据定位策略,提升图RAG在准确性和效率之间的平衡,实现高效且准确的知识检索。

摘要:

大型语言模型(LLMs)往往在固有知识边界和幻觉方面存在困难,限制了其在知识密集型任务中的可靠性。虽然检索增强生成(RAG)缓解了这些问题,但通常忽略了多跳推理中至关重要的结构性依赖关系。基于图的RAG方法试图弥合这一差距,但通常由于诸如成本高昂的图遍历和LLM生成摘要中的语义噪声等挑战,面临准确性和效率之间的权衡。在本文中,我们提出HyperNode扩展和逻辑路径引导的证据定位策略用于图RAG(HELP),这是一种新的框架,通过两种核心策略平衡准确性和实用性:1)HyperNode扩展,通过迭代地将知识三元组链接成连贯的推理路径,抽象为HyperNodes,以捕捉复杂的结构性依赖关系并确保检索准确性;2)逻辑路径引导的证据定位,利用预先计算的图-文本相关性将这些路径直接映射到语料库,以实现更高效的检索。HELP避免了昂贵的随机游走和语义扭曲,保持了知识的完整性,同时大幅减少了检索延迟。广泛的实验表明,HELP在多个简单和多跳QA基准测试中实现了竞争性的性能,并在领先的基于图的RAG基线中实现了高达28.8倍的速度提升。

英文摘要:

Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issues, it frequently overlooks structural interdependencies essential for multi-hop reasoning. Graph-based RAG approaches attempt to bridge this gap, yet they typically face trade-offs between accuracy and efficiency due to challenges such as costly graph traversals and semantic noise in LLM-generated summaries. In this paper, we propose HyperNode Expansion and Logical Path-Guided Evidence Localization strategies for GraphRAG (HELP), a novel framework designed to balance accuracy with practical efficiency through two core strategies: 1) HyperNode Expansion, which iteratively chains knowledge triplets into coherent reasoning paths abstracted as HyperNodes to capture complex structural dependencies and ensure retrieval accuracy; and 2) Logical Path-Guided Evidence Localization, which leverages precomputed graph-text correlations to map these paths directly to the corpus for superior efficiency. HELP avoids expensive random walks and semantic distortion, preserving knowledge integrity while drastically reducing retrieval latency. Extensive experiments demonstrate that HELP achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$\times$ speedup over leading Graph-based RAG baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑