Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
cs.CL, cs.AI
Submitted: 2026-05-11
Updated: 2026-11-10
Comments: NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Representation Engineering for Large-Language Models: Survey and Research Challenges
- Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
- Understanding (Un)Reliability of Steering Vectors in Language Models
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- The Llama 3 Herd of Models
- Contextual Linear Activation Steering of Language Models
- In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
- Steering Multimodal Large Language Models Decoding for Context-Aware Safety
- Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering
- Improving Instruction-Following in Language Models through Activation Steering
- Steering Language Models With Activation Engineering
- Extending Activation Steering to Broad Skills and Multiple Behaviours
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models
- Qwen2.5 Technical Report
- Instruction-Following Evaluation for Large Language Models
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data