Skip to content

Generative AI & LLMs

Top-p

Nucleus sampling

A generation setting that limits choices to a probability-based set of likely next tokens.

Example

Top-p sampling limits each choice to a set of likely tokens whose probabilities reach the chosen threshold.

Why people use it

Knowing how “Top-p” works helps teams choose and configure generative systems more effectively.

What you'll hear

“How does Top-p affect the answer the model gives the user?”

Related terms