SOURCE-LINKED INTELLIGENCE
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Safety alignment is usually posed as a topic-level question: is this subject harmful? Deployments ask a narrower one. A civics tutor and a public-sector assistant may share a base model yet need different boundaries inside the same topic, refusing targeted political manipulation while still answering factual questions about the same election. We formulate this as narrow-boundary safety and introduce an offline self-generated framework combining controlled topic generation, coverage repair, in-distribution compensation data, and harmful-benign pairs for training and evaluation. Single-shot gene
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-03T21:03:45.000Z
First collected: 2026-09-21T04:31:57.454Z. This is not the publication date.