Aligned LLMs exhibit Refusal-Escape Directions (RED) that enable refusal-to-answer transitions via input perturbations; these directions decompose exactly into operator-level sources, creating an inherent safety-utility trade-off when trying to eliminate them.
Advances in Neural Information Processing Systems , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
citing papers explorer
-
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
Aligned LLMs exhibit Refusal-Escape Directions (RED) that enable refusal-to-answer transitions via input perturbations; these directions decompose exactly into operator-level sources, creating an inherent safety-utility trade-off when trying to eliminate them.
-
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.