{
  "id": "self-correction",
  "code": "PTL-0117",
  "term": "Self-Correction",
  "aliases": [
    "intrinsic self-correction",
    "self-revision"
  ],
  "category": "verification",
  "definition": "Self-correction is the general practice of having a language model review and revise its own output, either from its own judgment alone (intrinsic self-correction) or using external feedback such as tool results, tests, or retrieved evidence.",
  "description": "Research has found that intrinsic self-correction does not reliably improve reasoning accuracy and can make answers worse, because the model often cannot tell which of its answers are wrong. Self-correction works best when the critique is grounded in something the model cannot fake, such as running code, executing a search, or checking against a reference.",
  "example": null,
  "broader": [],
  "narrower": [
    "critic"
  ],
  "related": [
    "self-refine",
    "reflexion",
    "chain-of-verification",
    "evaluator-optimizer"
  ],
  "introduced": 2023,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Large Language Models Cannot Self-Correct Reasoning Yet",
      "authors": "Huang et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2310.01798"
    }
  ],
  "url": "https://protologue.com/t/self-correction/",
  "citation": "Protologue. (2026). Self-Correction. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0117). https://protologue.com/t/self-correction/"
}