← Back to Glossary
Temperature
Phase 02 · LLM Fundamentalstechnique

A parameter controlling how randomly an LLM selects its next word — low values produce deterministic facts, high values produce creative outputs.

Why it exists

LLMs output probability distributions for the next token. Temperature scales these probabilities prior to sampling.

How it works

At temperature 0.0, the model always picks the single highest-probability token. At higher values (0.8+), lower probability tokens get a boost, introducing randomness.

Where you'll use this