AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment
AUDITPLAN is a single-model plan-then-answer approach where the model first emits a compact structured safety plan and then answers conditioned on it, enabling machine-checkable auditing while remaining hidden from users at deployment.
Sai Sri Pushpa Jampani, Kshitij Mishra, A. Ekbal
· 0 citations