Skip to content

Evaluation & Quality

Specificity

How often a system correctly leaves cases unflagged when the condition it looks for is absent.

Example

A detector correctly leaves 95 of 100 non-defective items unflagged.

Why people use it

It shows how often a detector correctly leaves ordinary cases unflagged.

What you'll hear

“How often does it correctly leave safe items alone?”

What this means for you

Consider specificity together with recall and the costs of both error types.

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

Can a rare condition make false alarms especially noticeable?
Yes. Even a small false-alarm rate can produce many alerts when most checked cases do not have the condition.
Can a detector get perfect specificity by flagging nothing?
Yes. It would also miss every genuine positive case, which shows why another measure is needed.
Does the score explain the cost of false alarms?
No. The same false-alarm rate can have very different practical consequences.

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