AI Tech Beacon

Retrieval-augmented generation

Combining two memories rather than enlarging one. A pre-trained sequence-to-sequence model supplies the parametric memory; a dense vector index,

Official source: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks →

reached through a neural retriever, supplies the non-parametric one. The founding work fine-tunes both together for generation, which is the distinction worth keeping: retrieval feeds generation here, instead of extracting an answer span the way earlier retrieval systems did.

Sources 1 source on record · Automated review 3 angles

Sources

What this page is based on — every source is verified and links out so you can check it yourself.

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksverified · 2026-08-15 · agent:verification