Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Lewis, P. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems.

Type

Preprint

Intellectual base

Grey literature

Year

2020

Link

https://arxiv.org/abs/2005.11401

Cited from

cognitive_science

Cited by

2 citations across 2 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Reality Monitoring
  • Cognitive science (origin) — the source-monitoring framework distinguishing memories of perceived events from imagined ones, and the systematic errors when the discrimination fails. Generative-AI safety — distinguishing retrieved factual claims from parametric hallucinations; retrieval-augmented architectures are essentially reality-monitoring systems that tag generations with source metadata.

    This sourceIntroduces retrieval-augmented generation, separating retrieved grounded claims from parametric model output.

Domain-specific

• Retrieval-augmented generation
  • Ordinary search ends with ranked records; ordinary generation need not consult external records; a prompt containing manually pasted text is context provision but not necessarily a maintained retrieval architecture.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Links previously used in the corpus

Before the registry existed this work was also linked 1 other way.

• https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html ×1

Registry ID ref:6dd4142abbba · see in the full table