SOURCE-LINKED INTELLIGENCE

AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket refusal on benign requests and polished but unfaithful safety rationales that do not actually constrain the answer. We propose AUDITPLAN, a single-model plan-then-answer approach where the model first emits a compact structured safety plan and then answers conditioned on it. The plan records a threat label, intended action, and explicit constraints, enabling machine-checkable auditing while remaining hidden from users at deployment. We train this b

Read original source ↗ Open in workspace

recordType

paper

region

Global