The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

ArXi:2605.26778v1 Announce Type: new Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually governs generation -- a prerequisite for any high-stakes deployment. The standard assumption, that context-consistent output implies context-governed output, breaks when the retrieved document overlaps with the model's pre