Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Quick summary
arXiv:2609.36388v1 Announce Type: new 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
Key takeaways
- arXiv:2609.36388v1 Announce Type: new 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.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments