Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
Paper • 2603.18280 • Published • 1
Greg Frank PRO
gregfrank
·
AI & ML interests
Alignment, mechanistic interpretability, model behavior, agentic red-teaming
Recent Activity
authored a paper about 1 month ago
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails authored a paper about 1 month ago
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models updated a collection about 1 month ago
alignmentOrganizations
None yet
authored 2
papers about 1 month ago
updated a
collection about 1 month ago
submitted a
paper to Daily Papers about 1 month ago