Temperature
Also called sampling temperature.
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.
Sources
- Holtzman et al. (2019). The Curious Case of Neural Text Degeneration.
Cite this entry
Protologue. (2026). Temperature. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0006). https://protologue.com/t/temperature/
BibTeX
@misc{protologue_temperature,
title = {Temperature},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0006},
url = {https://protologue.com/t/temperature/}
}