arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.04764cs.AI
收藏

Orion-RAG:无图数据的路径对齐混合检索

Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data

City University of Hong Kong(香港城市大学)

Zhen Chen, Weihao Xie, Peilin Chen, Shiqi Wang, Jianping Wang

AI总结:

Orion-RAG通过低复杂度路径提取方法,有效处理碎片化数据,实现跨文件信息链接,并在FinanceBench上取得25.2%的精度提升。

摘要:

检索增强生成(RAG)在知识综合中已证明有效,但在实际场景中,当数据本质上是离散和碎片化的时,会遇到显著挑战。在大多数环境中,信息分布在孤立的文件中,如报告和日志,这些文件缺乏显式的链接。标准搜索引擎独立处理文件,忽略它们之间的联系。此外,手动构建知识图谱对于如此庞大的数据来说是不现实的。为弥合这一差距,我们提出了Orion-RAG。我们的核心见解是简单而有效的:我们不需要复杂的算法来组织这些数据。相反,我们使用低复杂度的策略来提取轻量级路径,这些路径自然地将相关概念联系起来。我们证明,这种简洁的方法足以将碎片化文档转换为半结构化数据,使系统能够有效地在不同文件之间链接信息。广泛的实验表明,Orion-RAG在各种领域中均优于主流框架,支持实时更新和显式的Human-in-the-Loop验证,具有高成本效率。在FinanceBench上的实验显示,其精度优于强基线,相对提升达25.2%。

英文摘要:

Retrieval-Augmented Generation (RAG) has proven effective for knowledge synthesis, yet it encounters significant challenges in practical scenarios where data is inherently discrete and fragmented. In most environments, information is distributed across isolated files like reports and logs that lack explicit links. Standard search engines process files independently, ignoring the connections between them. Furthermore, manually building Knowledge Graphs is impractical for such vast data. To bridge this gap, we present Orion-RAG. Our core insight is simple yet effective: we do not need heavy algorithms to organize this data. Instead, we use a low-complexity strategy to extract lightweight paths that naturally link related concepts. We demonstrate that this streamlined approach suffices to transform fragmented documents into semi-structured data, enabling the system to link information across different files effectively. Extensive experiments demonstrate that Orion-RAG consistently outperforms mainstream frameworks across diverse domains, supporting real-time updates and explicit Human-in-the-Loop verification with high cost-efficiency. Experiments on FinanceBench demonstrate superior precision with a 25.2% relative improvement over strong 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。

↑