Fine-tuning updates frequently stale activation monitors for language model safety while quantization does not, with degradation predictable and repairable via label-free realignment.
arXiv preprint arXiv:2505.23556 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
OpenSafeIntent benchmark shows models fail to calibrate safety across intent shifts in matched dual-use prompts, indicating current evaluations are insufficient.
LANCE applies variational inference for label enhancement across multiple rejection categories, supplying gradients to a refinement model that produces safe, non-rigid responses from LLMs.
citing papers explorer
-
Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness
Fine-tuning updates frequently stale activation monitors for language model safety while quantization does not, with degradation predictable and repairable via label-free realignment.
-
OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets
OpenSafeIntent benchmark shows models fail to calibrate safety across intent shifts in matched dual-use prompts, indicating current evaluations are insufficient.
-
Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement
LANCE applies variational inference for label enhancement across multiple rejection categories, supplying gradients to a refinement model that produces safe, non-rigid responses from LLMs.