Fine-tuning updates frequently stale activation monitors for language model safety while quantization does not, with degradation predictable and repairable via label-free realignment.
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks //
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
background 1polarities
background 1representative citing papers
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
PROPEL amortizes solver evaluation with a trained activation probe to optimize task generators toward a target solve rate, raising the share of learnable tasks from ~10% to ~20% in coding and SWE experiments.
D²-Monitor routes between lightweight and heavy safety probes using the count of hesitation steps in diffusion LLM denoising trajectories, achieving SOTA trade-off on three datasets with under 0.85M parameters.
A boundary-targeted MIA strategy recovers 19% of distress-flagged conversations from a safety classifier at 5% false-positive rate, 3.5 times better than prior methods.
Probe trajectories across token positions in LRMs, combined with signal-processing features, improve prediction of future model outputs over static probes on safety and math tasks.
Multi-layer ensembles of linear probes raise AUROC for deception detection by up to 78% and probe accuracy scales with model size across 0.5B to 176B parameter models.
GCD uses diffusion model priors to guide suffix search, achieving higher attack success rates with better semantic adherence and lower detection than GCG-style methods.
Hidden-state probes enable low-overhead streaming moderation of LLM outputs by producing per-token safety scores from internal activations.
Prompt injection detection performance is highly regime-dependent with no single detector dominating across settings; transformer models perform best overall while structural signals offer modest gains in some regimes.
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.
-
Deep Minds and Shallow Probes
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
-
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
PROPEL amortizes solver evaluation with a trained activation probe to optimize task generators toward a target solve rate, raising the share of learnable tasks from ~10% to ~20% in coding and SWE experiments.
-
$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing
D²-Monitor routes between lightweight and heavy safety probes using the count of hesitation steps in diffusion LLM denoising trajectories, achieving SOTA trade-off on three datasets with under 0.85M parameters.
-
Boundary-targeted Membership Inference Attacks on Safety Classifiers
A boundary-targeted MIA strategy recovers 19% of distress-flagged conversations from a safety classifier at 5% false-positive rate, 3.5 times better than prior methods.
-
Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics
Probe trajectories across token positions in LRMs, combined with signal-processing features, improve prediction of future model outputs over static probes on safety and math tasks.
-
Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling
Multi-layer ensembles of linear probes raise AUROC for deception detection by up to 78% and probe accuracy scales with model size across 0.5B to 176B parameter models.
-
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance
GCD uses diffusion model priors to guide suffix search, achieving higher attack success rates with better semantic adherence and lower detection than GCG-style methods.
-
Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs
Hidden-state probes enable low-overhead streaming moderation of LLM outputs by producing per-token safety scores from internal activations.
-
Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals
Prompt injection detection performance is highly regime-dependent with no single detector dominating across settings; transformer models perform best overall while structural signals offer modest gains in some regimes.