Year: 2026
Type: conference-paper
Abstract: Personalized Large Language Models (LLMs) facilitate more 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 demonstrate the existence of situation-dependency and consistent situation-behavior patterns within LLM personalities through a multi-perspective analysis of persona neurons.Building on these insights, we propose IRIS, a training-free, neuron-based Identify-Retrieve-Steer framework for advanced situational personality steering.Our approach comprises situational persona neuron identification, situation-aware neuron retrieval, and similarity-weighted steering.We empirically validate our framework on PER-SONALITYBENCH and our newly introduced SPBench, a comprehensive situational personality benchmark.Experimental results show that our method surpasses best-performing baselines, demonstrating IRIS's generalization and robustness to complex, unseen situations and different models architecture.
Authors: Zesheng Wei, Mengxiang Li, Zilei Wang, Yang Deng
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166804503