AIBullisharXiv – CS AI · Mar 56/10
🧠
Controllable and explainable personality sliders for LLMs at inference time
Researchers propose Sequential Adaptive Steering (SAS), a new framework for controlling Large Language Model personalities at inference time without retraining. The method uses orthogonalized steering vectors to enable precise, multi-dimensional personality control by adjusting coefficients, validated on Big Five personality traits.