AI RESEARCH
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
arXiv CS.LG
•
ArXi:2605.20262v1 Announce Type: new We study selective refusal editing as a three-way control problem: induce non-refusal on designated edit prompts while preserving benign behavior and harmful refusals outside the edit set. We