AI RESEARCH
Beyond Static Personas: Situational Personality Steering for Large Language Models
arXiv CS.CL
•
ArXi:2604.13846v1 Announce Type: new Personalized Large Language Models (LLMs) facilitate natural, human-like interactions in human-centric applications. However, existing personalization methods are constrained by limited controllability and high resource demands. Furthermore, their reliance on static personality modeling restricts adaptability across varying situations. To address these limitations, we first nstrate the existence of situation-dependency and consistent situation-behavior patterns within LLM personalities through a multi-perspective analysis of persona neurons.