AI RESEARCH
Decoupling Knowledge and Task Subspaces for Composable Parametric Retrieval Augmented Generation
arXiv CS.CL
•
ArXi:2604.26768v1 Announce Type: new Parametric Retrieval-Augmented Generation (PRAG) encodes external documents into lightweight parameter modules that can be retrieved and merged at inference time, offering a promising alternative to in-context retrieval augmentation. Despite its potential, many PRAG implementations train document adapters with task-supervised objectives, which may cause each adapter to encode both document-specific facts and reusable task-solving behavior.