Persona Dosing: Calibrated Activation Steering for Graded Trait Control
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
- The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
- Controllable and explainable personality sliders for LLMs at inference time
- Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
- Learning a Generative Meta-Model of LLM Activations
- UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
- Steering Language Models With Activation Engineering
- ReFT: Representation Finetuning for Language Models
- Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
- 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