SOURCE-LINKED INTELLIGENCE

Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation. Standard robustness evaluations conflate stage-level failures into a single end-to-end metric, obscuring both the source of brittleness and the appropriate mitigation target. We ask which stage fails, and why, when the pipeline is subjected to adversarial perturbations on the input question. We introduce a stage-isolation protocol with two answer-preserving adversarial perturbations verified against the knowledge g

Read original source ↗ Open in workspace

recordType

paper

region

Global