{
  "@context": "https://schema.org",
  "@type": "TechArticle",
  "@id": "https://anchorfact.org/kb/kb-2026-00006",
  "headline": "Retrieval-Augmented Generation (RAG)",
  "description": "Retrieval-Augmented Generation (RAG) is an AI architecture introduced by Lewis et al. (2020) at Facebook AI Research that combines large language models with real-time external knowledge retrieval. Instead of relying solely on parametric knowledge (what the model memorized during training), RAG retrieves relevant documents from a knowledge base and provides them as context for generation. This reduces hallucination by ~50% in empirical studies, enables responses grounded in up-to-date and domain-specific information, and provides source attribution. RAG underpins AI search engines (Perplexity, Google AI Overviews, ChatGPT Search), enterprise knowledge bases, and research assistants (Elicit, Consensus) — making it the dominant architecture for production AI systems requiring factual accuracy.",
  "dateCreated": "2026-05-22T14:59:47.501Z",
  "dateModified": "2026-05-22T14:59:47.501Z",
  "author": {
    "@type": "Organization",
    "name": "AnchorFact"
  },
  "publisher": {
    "@type": "Organization",
    "name": "AnchorFact",
    "url": "https://anchorfact.org"
  },
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "anchorfact:confidence": "high",
  "anchorfact:generationMethod": "human_only",
  "citation": []
}