Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Paper • 2609.36388 • Published • 54
Hudson Liu
hudson-liu71
AI & ML interests
Alignment-focused model research.
Recent Activity
liked a model 2 days ago
jialinyyzz/humanizer upvoted a paper 4 days ago
Persona Dosing: Calibrated Activation Steering for Graded Trait Control upvoted a paper 4 days ago
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?Organizations
None yet