AI Safety & Responsible AI
Explainability
XAI
Methods that help people understand why an AI system produced a particular result.
Example
A lender provides a meaningful reason for an automated application decision.
Why it matters
It helps people understand, question or correct decisions that affect them.
You'll hear it
“What changed the recommendation in this case?”
Can you control it?
Sometimes
Sometimes. Some products or workflows let you influence explainability, while others keep it fixed or manage it automatically. Check the settings and documentation for the tool you are using.
Common questions
- Can a plausible explanation be inaccurate?
- Yes. A generated explanation may not faithfully reflect what influenced the result.
- Does explaining a decision prove it was fair?
- No. Understandable reasons can still be mistaken or unjustified.
- Does everyone need the same explanation?
- No. A user, reviewer and developer may need different kinds of detail.