Jung-Eun Kim

The paper argues that the 'positive backdoor' label should be retired and replaced with 'Secret Alignment,' asserting that all such protective claims require rigorous, standardized evaluation due to inherent brittleness.

The paper argues that the 'positive backdoor' label should be retired and replaced with 'Secret Alignment,' asserting that such protective claims must be rigorously evaluated for security, especially concerning confidentiality, integrity, and availability.

DenseSteer is a training-free inference-time framework that improves the math reasoning capabilities of small language models by steering their internal representations toward a 'Dense Reasoning' pattern.