Knowledge cutoff
Also: training cutoff, cutoff date
The date the model's training data ends. It knows nothing after that unless you give it the information.
up to the cutoff
after the cutoff
A new case, a new rule, or last month’s news is simply absent unless you paste it in or the app searches for it. Ask the tool what its cutoff is.
The fuller definition
A knowledge cutoff is the date after which a model's training data was not collected. Events, decisions, and rule changes after that date are unknown to the model unless they are supplied in context or retrieved.
Go deeper
- ExamplesInputs paired with the expected output.
- PredictionThe model produces an output.
- LossHow far off it was, as a number.
- UpdateParameters nudged to reduce the loss; repeat.
Training ends at the knowledge cutoff. Whatever the examples contained, including their gaps and biases, is what the model learned.
A concrete example
A model with a 2025 cutoff cannot know a 2026 amendment unless the amended text is supplied or searched.
The distinction that matters
A cutoff is not a guarantee of complete knowledge before that date. Coverage of any topic can be partial or wrong.
Related terms
Training
Adjusting a model with examples and a learning rule. The aim is to improve how it handles tasks.
Documents & retrievalRetrieval
Searching a larger set of records for useful parts. Finding a passage does not prove it answers the question.
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
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe 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.