Retrieval-Augmented Generation
The RAG paper combines parametric sequence generation with retrieved documents from a non-parametric index. It evaluates knowledge-intensive tasks where access to external passages can support generation.
Overview. The RAG paper combines parametric sequence generation with retrieved documents from a non-parametric index.
Context. It evaluates knowledge-intensive tasks where access to external passages can support generation.
Claims and evidence
Claim ledger, 2The RAG paper combines parametric sequence generation with retrieved documents from a non-parametric index.
It evaluates knowledge-intensive tasks where access to external passages can support generation.