SafeGene extracts task-transferable safety vectors from model discrepancies and applies them through layer-wise recalibration to reduce harmful outputs in downstream-adapted LLMs without retraining.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SafeGene: Reusable Adapters for Transferable Safety Alignment
SafeGene extracts task-transferable safety vectors from model discrepancies and applies them through layer-wise recalibration to reduce harmful outputs in downstream-adapted LLMs without retraining.