Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior
cs.LG, cs.CL
Submitted: 2026-06-07
Updated: 2026-11-11
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- The Llama 3 Herd of Models
- A Unified Understanding and Evaluation of Steering Methods
- ATLAS: Verifier-Guided Adaptive Latent Activation Steering for Efficient LLM Reasoning
- Qwen2 Technical Report
- Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories
- ShareChat: A Dataset of Chatbot Conversations in the Wild
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis