{
  "id": "self-taught-reasoner",
  "code": "PTL-0086",
  "term": "Self-Taught Reasoner",
  "aliases": [
    "STaR"
  ],
  "category": "test-time",
  "definition": "The Self-Taught Reasoner (STaR) bootstraps reasoning ability by having a model generate rationales, keeping those that lead to correct answers, and fine-tuning on them in repeated rounds.",
  "description": "For problems it fails, STaR provides the correct answer as a hint and asks the model to produce a rationale for it, a step called rationalization.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "reasoning-model",
    "chain-of-thought"
  ],
  "introduced": 2022,
  "sources": [
    {
      "title": "STaR: Bootstrapping Reasoning With Reasoning",
      "authors": "Zelikman et al.",
      "year": 2022,
      "url": "https://arxiv.org/abs/2203.14465"
    }
  ],
  "url": "https://protologue.com/t/self-taught-reasoner/",
  "citation": "Protologue. (2026). Self-Taught Reasoner. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0086). https://protologue.com/t/self-taught-reasoner/"
}