Skip to content
Research

The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language Models.

arXiv:2610.09493v1 Announce Type: new Abstract: A retrieval-augmented model can match a document without relying on it. Controlled knowledge conflicts make source choice observable and let us ask a second question that prediction alone cannot answer: which int

arXiv cs.AIResearch source·