On the Steering Dimensionality of Refusal in Language Models

arXiv:2610.04245 · cs.AI · Submitted 2026-10-03 · Read on arXiv

cs.AI

Submitted: 2026-10-03

Updated: 2026-10-03

Comments: InterpScience Workshop at NeurIPS 2026

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

Terminology

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

Sources

• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
• When is Your LLM Steerable?
• The Llama 3 Herd of Models
• Gemma 4 Technical Report
• Steering Language Models With Activation Engineering
• Qwen3 Technical Report
• Representation Engineering: A Top-Down Approach to AI Transparency

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