Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models

ArXi:2602.16608v2 Announce Type: replace-cross Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification, and lack context-awareness of inter-token dependencies and structural components. They also fail to capture how relevance evolves across layers and how structural components shape decision-making.