Amazon Nova Uses rDPO for Selective Unlearning

Let's Data Science – AI Governance(Global) 8 Jul 2026 52

Adapter-scoped safety customisation on a major cloud model family could reshape how APS teams govern sensitive AI workloads on AWS Bedrock.

  • AWS introduced rDPO, a LoRA-adapter technique enabling approved enterprise customers to reduce model over-deflection in selected safety categories.
  • The approach separates configurable moderation behaviour from non-configurable protections, potentially relevant for government security, legal, and research workloads.
  • All benchmark results are vendor-reported; independent validation of residual risk and governance boundaries is still required before reliance.
  • Monitor Agencies using AWS Bedrock for sensitive workloads may want to monitor CCMS availability, approved-customer eligibility, and any independent evaluations of residual risk.
  • Consider AI governance teams could consider how adapter-scoped safety customisation interacts with existing agency-level AI risk assessments and vendor management obligations under the APS AI Policy.

Implications are AI-generated. Starting points, not advice — see methodology for how they're framed.

View original source