Refusal

Definitions

1. A response pattern in which an AI system declines to comply with a request because it is unsafe, disallowed, unsupported, or outside system boundaries. Good refusal behavior aims to be firm, clear, and not overly restrictive on benign requests.

   In plain English: An AI response that declines to do something.

   Example: "The compliance team reviewed refusal quality because the assistant needed to decline risky requests without blocking routine legitimate work."

Related Terms

• AI Sandbox
• Interpretability
• Model Safety
• Moderation
• Prompt Safety
• Safety Evaluation
• Safety Policy
• Safety Testing
• Safety Training