Temperature
A setting that affects how varied the output may be. Lower values often make it less varied. They do not ensure the same answer each time.
Always picks the most likely next word. Ask twice, get the same answer twice.
Sometimes picks a less likely word. Ask twice, get two different answers.
Neither setting makes the answer more true. Low temperature makes mistakes repeatable; high temperature makes them varied.
The fuller definition
Temperature is a sampling parameter that changes the relative spread of token probabilities before selection. Lower values generally concentrate choices; higher values can increase variation.
Go deeper
Invented probabilities. Always picking the top candidate gives the same wording every run; sampling sometimes picks a lower one. Neither setting checks whether the sentence is true.
A concrete example
You compare a more restrained and a more varied continuation of a fictional sentence.
The distinction that matters
Temperature is not a truth setting, and zero does not guarantee identical results across all systems.
Related terms
Sampling
How the model picks the next word from its list of likely candidates. It can always take the top one, or roll the dice among the top few.
Training & generationTop-p sampling
A setting that narrows the next-token choices. It keeps a group with a set share of the total chance. Lower values usually narrow that group.
Reliability & securityHallucination
When the model states something that sounds right but is made up, including cases, quotes, and facts that do not exist.
Where it is taught
How models learn from examplesSource and further reading
Hugging Face · LLM courseThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.