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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Zhen, Xie, Weihao, Chen, Peilin, Wang, Shiqi, Wang, Jianping
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914240265191424
author Chen, Zhen
Xie, Weihao
Chen, Peilin
Wang, Shiqi
Wang, Jianping
author_facet Chen, Zhen
Xie, Weihao
Chen, Peilin
Wang, Shiqi
Wang, Jianping
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04764
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data
Chen, Zhen
Xie, Weihao
Chen, Peilin
Wang, Shiqi
Wang, Jianping
Artificial Intelligence
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.
title Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data
topic Artificial Intelligence
url https://arxiv.org/abs/2601.04764