# Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela

2020 | arXiv:2005.11401

Source: https://arxiv.org/abs/2005.11401

Reading scope: abstract-and-metadata

Editorial update: 2026-10-20

A pretrained sequence generator uses a searchable external memory.

## Why this matters

It names a concrete retrieval-and-generation training recipe.

## The proposal

The authors combine parametric memory with retrieved documents for generation. Their two formulations differ in whether passages remain fixed across a sequence or may vary by token.

## What was inspected

The abstract reports QA and generation comparisons. We have not audited the tables or provenance behavior; reported factuality gains are not a guarantee for individual answers.

## Editorial interpretation

Use this paper as a reference point, not the origin of all retrieval research. Later systems can share the RAG label while using different training and retrieval arrangements.

## Mechanism

Search a dense Wikipedia index.

Condition generation on passages.

Compare sequence-level and token-level passage conditioning.

## Limits

Retrieved text does not guarantee factual output.

The inspected abstract is not a modern deployment guide.