{
  "id": "temperature",
  "code": "PTL-0006",
  "term": "Temperature",
  "aliases": [
    "sampling temperature"
  ],
  "category": "foundations",
  "definition": "Temperature is a sampling parameter that rescales a model's output probabilities before a token is chosen; lower values make outputs more deterministic and higher values make them more varied.",
  "description": "At temperature zero the model approximately always picks its most likely token (greedy decoding). Techniques that rely on diverse samples, such as self-consistency and best-of-N, deliberately use a nonzero temperature, while extraction and classification tasks usually use a low one.",
  "example": null,
  "broader": [],
  "narrower": [],
  "related": [
    "top-p-sampling",
    "self-consistency",
    "best-of-n-sampling"
  ],
  "introduced": null,
  "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/temperature/",
  "citation": "Protologue. (2026). Temperature. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0006). https://protologue.com/t/temperature/"
}