Skip to content

Evaluation & Quality

True negative

A correct all-clear: the system says a condition is absent, and it really is absent.

Example

A filter correctly leaves a legitimate email out of the spam folder.

Why people use it

It records a case where the system correctly found no problem.

What you'll hear

“The safe message stayed in the inbox.”

What this means for you

Review all parts of the confusion matrix.

Can you control it?

No

No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.

Common questions

Is a large true-negative count enough to show a good detector?
No. Common negative cases can dominate while positive cases are missed.
Does 'negative' always mean a bad outcome?
No. It names one side of a test, often the absence of the condition being checked.
Can this count be high simply because ordinary cases are common?
Yes. A large count needs background information about the whole set of cases.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice