What is Temperature?

A decoding strategy that samples only from the k most likely next tokens.

A decoding strategy that samples from the smallest token set whose probabilities sum to p.

Aligning user confidence in AI outputs with the system's actual reliability in each task.

Systematic unfairness in model outputs caused by skewed data, assumptions, or modeling choices.

The process of assigning tags or target outputs to raw data for supervised learning.

Trusted reference labels used to train or evaluate model outputs.