The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content

arXiv:2606.11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution. We identify and formalise a phenomenon we term the structural...

Läs hela artikeln hos källan.