AI safety and alignment · MLD-0231
Corrigibility
A system property involving receptiveness to correction, intervention, or shutdown by appropriate overseers.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Study whether an agent cooperates with authorized correction.
Original caveat
A verbal promise to accept correction is not sufficient evidence.
Context and aliases
Level: Advanced. Stages: Training · Evaluation · Research · Governance.
Tags: Safety · RL · SLM · LLM.
Aliases: None recorded.