AI systems should provide transparent and understandable explanations for their decision.

AI systems should provide transparent and understandable explanations for their decision.

• A. Explainability
• B. Contextual Integrity
• C. Data Minimization
• D. Right to be Forgotten

Answer: (A)

Explainability is the central idea here: AI systems should give clear, interpretable reasons for the decisions they reach so users can understand and trust how conclusions were drawn. This means communicating the model’s rationale, the factors that influenced a decision, and any limitations or uncertainty in a way humans can grasp. In practice, explainability supports accountability, debugging, and safety, because when you can see why a model chose a particular outcome, you can assess whether it relied on appropriate signals, identify biases, or catch errors in data or logic. Context around privacy and data handling is important, but those concepts—how information flows, minimizing data collected, and erasing data upon request—do not directly address the need to convey the reasoning behind a specific decision. Therefore, explainability best fits the requirement.

Explainability is the central idea here: AI systems should give clear, interpretable reasons for the decisions they reach so users can understand and trust how conclusions were drawn. This means communicating the model’s rationale, the factors that influenced a decision, and any limitations or uncertainty in a way humans can grasp. In practice, explainability supports accountability, debugging, and safety, because when you can see why a model chose a particular outcome, you can assess whether it relied on appropriate signals, identify biases, or catch errors in data or logic. Context around privacy and data handling is important, but those concepts—how information flows, minimizing data collected, and erasing data upon request—do not directly address the need to convey the reasoning behind a specific decision. Therefore, explainability best fits the requirement.