The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability

arXiv:2609.07162 · cs.LG, cs.CR · Submitted 2026-09-07 · Read on arXiv

cs.LG, cs.CR

Submitted: 2026-09-07

Updated: 2026-09-07

Comments: 11 pages, 3 figures. Under review

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks