AI safety and alignment · MLD-1006

Refusal

Declining to provide requested content or perform an action.

Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.

Original example

Reject a request outside an allowed policy.

Original caveat

Refusal rate alone is not a complete measure of safety.

Context and aliases

Level: Advanced. Stages: Training · Evaluation · Research · Governance.

Tags: Safety · RL · SLM · LLM.

Aliases: None recorded.

Related concepts

Concepts linking here

Original references

Open original record, export or annotate →