Decoupling Error Attribution in Cloud-Native Graph-RAG: A Data Integrity Diagnostic Framework

2026-09-10

AI Summary

本文提出一个三层解耦诊断框架，解决云原生图-RAG系统中数据完整性问题，通过归因系统错误到推理损失、知识图谱缺陷和Cypher生成错误。

Abstract

Graph-RAG systems often assume pristine data quality, overlooking the severe impact of perturbations in cloud-native databases. This paper proposes a three-layer decoupled diagnostic framework to orthogonally attribute system errors to reasoning loss, Knowledge Graph (KG) defects, and Cypher generation errors. Evaluated on a spatio-temporal ecological KG of the Southeastern Tibet region with eight defect types, results reveal that data integrity, rather than algorithmic reasoning, is the dominant performance bottleneck, with structural defects degrading system accuracy from 0.93 to 0.39. Crucially, we observe a masking-like phenomenon termed the Parametric Knowledge Masking Effect (PKME), suggesting LLMs compensate for broken retrieval paths using internal memory. This shrinks apparent query generation errors by over 70 percent, obscuring actual storage deterioration and increasing the risk of false negatives for automated monitoring. This work provides a quantitative foundation for auditing and optimizing data integrity in cloud-based information fusion systems.

Problem

• Data Integrity
• Graph-RAG
• Cloud-Native Databases
• Structural Defects
• Parametric Knowledge Masking Effect

Innovation

• three-layer decoupled diagnostic framework
• data integrity
• Parametric Knowledge Masking Effect (PKME)
• Knowledge Graph defects