mlsanityData to 14 Oct 2026

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

arXiv 2609.13324 ↗First posted 10 Sep 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 10 of its 12 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

10 of 12 references.

References · 10

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  3. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  5. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  7. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  8. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  9. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
  10. 2023Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modelingcited by 56

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation
  2. 2024Cloud Atlas: Efficient Fault Localization for Cloud Systems using Language Models and Causal Insight
  3. 2025Kunlun Anomaly Troubleshooter: Enabling Kernel-Level Anomaly Detection and Causal Reasoning for Large Model Distributed Inference
  4. 2025Enhancing reliability in AI inference services: An empirical study on real production incidents
  5. 2026Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems
  6. 2026Diagnosing and Repairing Factual Errors in RAG under Budget Constraints
  7. 2026Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents
  8. 2026RAGStress: A controlled benchmark for evaluating retrieval-augmented generation under knowledge-base degradation