{
  "id": "greedy-decoding",
  "code": "PTL-0109",
  "term": "Greedy Decoding",
  "aliases": [
    "argmax decoding",
    "temperature 0"
  ],
  "category": "foundations",
  "definition": "Greedy decoding generates text by always choosing the single most probable next token, which makes output deterministic for a given prompt and model.",
  "description": "It is the limit of sampling as temperature approaches zero and is often used when consistency matters, as in extraction or classification. For open-ended text it tends to produce bland or repetitive output, and for reasoning tasks sampling several answers and voting, as in self-consistency, usually beats a single greedy answer.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "temperature",
    "top-k-sampling",
    "top-p-sampling",
    "self-consistency",
    "text-degeneration"
  ],
  "introduced": null,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "The Curious Case of Neural Text Degeneration",
      "authors": "Holtzman et al.",
      "year": 2019,
      "url": "https://arxiv.org/abs/1904.09751"
    }
  ],
  "url": "https://protologue.com/t/greedy-decoding/",
  "citation": "Protologue. (2026). Greedy Decoding. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0109). https://protologue.com/t/greedy-decoding/"
}