发表机构
Chengdu Jincheng College（成都锦城学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对云原生图RAG中数据扰动被忽视的问题，提出三层解耦诊断框架，发现数据完整性是主要瓶颈，并揭示参数化知识掩蔽效应，为数据完整性审计提供定量依据。
AI 中文摘要
图RAG系统通常假设数据质量纯净，忽视了云原生数据库中扰动带来的严重影响。本文提出一个三层解耦诊断框架，将系统错误正交归因于推理损失、知识图谱缺陷和Cypher生成错误。在西藏东南部地区的一个时空生态知识图谱上，针对八种缺陷类型进行评估，结果表明数据完整性而非算法推理是主导性能瓶颈，其中结构缺陷使系统准确率从0.93降至0.39。关键的是，我们观察到一种类似掩蔽的现象，称为参数化知识掩蔽效应（PKME），表明大语言模型利用内部记忆补偿断裂的检索路径。这使表面上的查询生成错误缩减超过70%，掩盖了实际存储退化，增加了自动化监控的漏报风险。本工作为云基信息融合系统中数据完整性的审计与优化提供了定量基础。
英文摘要
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.
CommentsAccepted by ICCCBDA 2026
