Skip to content
Research

AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment.

arXiv:2609.19325v1 Announce Type: cross Abstract: 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

arXiv cs.AIResearch source·