MORAIDICTIONNAIRE IA
Inférence & Prompting

Temperature

The dial that tunes a model's boldness: from utterly predictable to wildly creative.

Temperature is the dial that decides how much risk a language model is willing to take. Picture a slider: all the way left, the model plays it safe and always repeats the most likely word; all the way right, it grows bold, surprising, sometimes incoherent. It is a sampling parameter applied at inference time, leaving the model's weights untouched.

How it works

A model doesn't predict a single word but a probability distribution over its entire vocabulary. Temperature $T$ divides the raw scores (logits) before the softmax step:

$$P(x_i) = \frac{\exp(z_i / T)}{\sum_j \exp(z_j / T)}$$

Choosing the right value

Temperature Behaviour Typical use
0 – 0.3 Precise, repeatable Code, extraction, math, facts
0.5 – 0.8 Balanced Writing, dialogue
1.0 – 1.5 Creative, varied Brainstorming, poetry, fiction

The core trade-off

Temperature embodies the trade-off between reliability and diversity. Too low, and answers turn monotonous and rigid; too high, and they drift toward incoherence and hallucination. It is often combined with other controls such as top-p (nucleus sampling) to better govern the window of possible choices.

Tuning the temperature doesn't make the model "smarter" — it lets you choose between caution and imagination.

Explore the full AI dictionary →