Explainability
Being able to say why an AI system produced a given output.
Explainability lets people understand the factors behind a model’s output, which matters for challenging decisions, regulatory duties, debugging and trust. The level needed rises with the impact of the decision.
On the exam
If affected people can’t be told why a decision was made, explainability is the missing property.
Related terms
- Human in the loopA person reviews or can override an AI system’s decisions.
- Bias and fairnessWhether an AI system treats groups of people unfairly.
Test yourself with today’s question of the day.