{
  "id": "corrective-rag",
  "code": "PTL-0135",
  "term": "Corrective RAG",
  "aliases": [
    "CRAG"
  ],
  "category": "retrieval-tools",
  "definition": "Corrective RAG (CRAG) adds a lightweight evaluator that grades retrieved documents for relevance and, depending on the grade, uses them, discards them in favor of web search, or combines both before generation.",
  "description": "It targets the failure where poor retrieval silently produces a confident wrong answer. Retrieved documents are also decomposed into smaller strips and filtered so that only relevant parts reach the generator. The method plugs into existing RAG pipelines without retraining the generator.",
  "example": null,
  "broader": [
    "retrieval-augmented-generation"
  ],
  "narrower": [],
  "related": [
    "self-rag",
    "agentic-rag",
    "web-search-tool"
  ],
  "introduced": 2024,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Corrective Retrieval Augmented Generation",
      "authors": "Yan et al.",
      "year": 2024,
      "url": "https://arxiv.org/abs/2401.15884"
    }
  ],
  "url": "https://protologue.com/t/corrective-rag/",
  "citation": "Protologue. (2026). Corrective RAG. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0135). https://protologue.com/t/corrective-rag/"
}