The degree to which the reasoning behind an AI system's outputs can be understood and explained to people.
Explainability is the ability to describe, in human terms, why an AI system produced a particular output. It supports trust, accountability, and the ability to challenge or correct decisions, especially for individuals affected by them.
Many high-performing models are opaque, so explainability often relies on supporting techniques and documentation. It is closely linked to transparency requirements in AI governance and the EU AI Act.
KaitoSec