[2603.03326] Controllable and explainable personality sliders for LLMs at inference time

Computer Science > Computation and Language arXiv:2603.03326 (cs) [Submitted on 10 Feb 2026] Title:Controllable and explainable personality sliders for LLMs at inference time Authors:Florian Hoppe, David Khachaturov, Robert Mullins, Mark Huasong Meng View a PDF of the paper titled Controllable and explainable personality sliders for LLMs at inference time, by Florian Hoppe and 3 other authors View PDF HTML (experimental) Abstract:Aligning Large Language Models (LLMs) with specific personas typically relies on expensive and monolithic Supervised Fine-Tuning (SFT) or RLHF. While effective, these methods require training distinct models for every target personality profile. Inference-time activation steering offers a parameter-efficient alternative, yet naive approaches fail to control multiple traits simultaneously due to destructive vector interference. In this work, we propose a modular framework for continuous, multi-dimensional personality control. Our key innovation is Sequential Adaptive Steering (SAS): a method that orthogonalizes steering vectors by training subsequent probes on the residual stream shifted by prior interventions. This approach transforms steering vectors into reusable primitives, allowing users to instantly synthesize complex, high-fidelity personality profiles by simply adjusting coefficients alpha. We validate our framework on the Big Five personality traits, demonstrating that it outperforms naive baselines in both goal adherence and coherence, en...