Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data
This addresses the challenge of knowledge synthesis in practical scenarios with discrete, unlinked data, though it appears incremental as it builds on existing RAG frameworks.
The paper tackles the problem of retrieving information from fragmented, graphless data like isolated files, where standard search engines ignore connections between documents. It presents Orion-RAG, which uses a low-complexity strategy to extract lightweight paths linking related concepts, achieving a 25.2% relative improvement in precision over baselines on FinanceBench.
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.