{
  "id": "chain-of-draft",
  "code": "PTL-0116",
  "term": "Chain of Draft",
  "aliases": [
    "CoD",
    "concise chain-of-thought"
  ],
  "category": "reasoning",
  "definition": "Chain of Draft is a variant of chain-of-thought prompting in which the model writes only a minimal draft of each reasoning step, a few words rather than full sentences, to reach an answer with far fewer tokens.",
  "description": "The authors report accuracy comparable to standard chain-of-thought on arithmetic, commonsense, and symbolic tasks while using a small fraction of the output tokens, which lowers cost and latency. It is most useful where reasoning helps but verbose explanations are not needed.",
  "example": "Think step by step, but keep only a minimum draft for each step, five words at most. Give the answer after ####.",
  "broader": [
    "chain-of-thought"
  ],
  "narrower": [],
  "related": [
    "prompt-compression",
    "skeleton-of-thought",
    "overthinking"
  ],
  "introduced": 2025,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Chain of Draft: Thinking Faster by Writing Less",
      "authors": "Xu et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2502.18600"
    }
  ],
  "url": "https://protologue.com/t/chain-of-draft/",
  "citation": "Protologue. (2026). Chain of Draft. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0116). https://protologue.com/t/chain-of-draft/"
}