VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations
cs.CL, cs.AI, cs.LG, cs.MA
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Steering Geometry: Validating Human Value Geometry in LLM Steering Space
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation
- Dual Mechanisms of Value Expression: Intrinsic vs. Prompted Values in Large Language Models
- Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
- Mistral 7B
- Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
- Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering
- Effectively Steer LLM To Follow Preference via Building Confident Directions
- Qwen2.5 Technical Report
- Steering Language Models With Activation Engineering
- Extending Activation Steering to Broad Skills and Multiple Behaviours
- LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance
- LegiLM: A Fine-Tuned Legal Language Model for Data Compliance
- 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