When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety
cs.AI, cs.CL, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/tatsu-lab/stanford_alpaca
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
- Training Verifiers to Solve Math Word Problems
- Unsupervised Concept Vector Extraction for Bias Control in LLMs
- SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
- Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
- The Llama 3 Herd of Models
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
- Adversarial Robustness of Activation Steering in Large Language Models
- Qwen2.5 Technical Report
- Steering Without Side Effects: Improving Post-Deployment Control of Language Models
- Steering Language Models With Activation Engineering
- Ethical and social risks of harm from Language Models
- Holistic Safety and Responsibility Evaluations of Advanced AI Models
- Qwen3Guard 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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection