Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers

arXiv:2610.01495 · cs.AI · Submitted 2026-10-01 · Read on arXiv

cs.AI

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 36 pages (9 pages main text)

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

Terminology

• Transformer — 1× in this paper · explained in 2 episodes

Sources

• The Internal State of an LLM Knows When It's Lying
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Attention Residuals
• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems