Recalln.

Of all the truly AI-written texts a detector is shown, the fraction it correctly identifies. A detector can have high accuracy but low recall — missing most AI text — if it sets its threshold cautiously. Recall and false-positive rate together describe a detector far better than a single accuracy number.


Put it into practice

Paste any text to see how likely it reads as AI — with the same calibrated three-way breakdown this glossary describes.

Try the free AI detector →
In the journal

Where Recall comes up.