Persona Dosing: Calibrated Activation Steering for Graded Trait Control

2026-09-28

AI Summary

This study addresses the absence of behavioral scales for precisely modulating the expression intensity of personality traits in large language models by proposing PersonaDose. This method integrates a descriptive conditioning controller (FLAS) with flow-time calibration, decoupling the controller’s learning range from query precision to enable graded control of personality traits based on target intensities without requiring paired target-intensity data. Experimental results demonstrate that PersonaDose significantly improves the expression accuracy of core personality traits on models such as Llama, achieving an average positioning error of only 4.7–6.2 points and outperforming activation addition baselines.

Abstract

An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We study persona dosing: controlling a language model through a trait description and a requested mean intensity. PersonaDose specializes a shared, description-conditioned FLAS controller on persona responses, then calibrates its flow time against measured trait expression. Training responses are not paired with requested target intensities. Across Llama-3.1-8B, Qwen3-8B, and Gemma-3-4B, PersonaDose raises core-trait expression at the Persona Vectors coherence floor of 75 by 33.2, 18.3, and 17.8 points over contrastive activation addition. Calibration-selected settings retain an expression advantage on held-out questions, although the coherence floor does not hold for every trait there. Across seven trained traits, calibrated requests yield mean targeting errors of 4.7-6.2 points over 14-22 calibration-reachable targets out of 28 per model. These results separate the behavioral range learned by a controller from the accuracy of requests within that range.

Problem

• persona dosing
• activation steering
• trait control
• language model
• calibration

Innovation

• Persona Dosing
• Activation Steering
• Calibrated Control
• FLAS Controller
• Trait Expression