1
Persona Dosing: Calibrated Activation Steering for Graded Trait Control
PersonaDose trains a description‑conditioned FLAS controller to steer LLM persona traits and calibrates flow time to hit a requested intensity, without needing intensity‑labeled data. Across Llama‑3.1‑8B, Qwen3‑8B, and Gemma‑3‑4B it boosts trait expression by up to 33 points and achieves mean targeting errors of 4.7‑6.2 points over reachable targets.
Hugging Face Daily Papersarxiv.org1 minpaper