ACL Findings2026
Beyond Static Personas: Situational Personality Steering for Large Language Models
Zesheng Wei, Mengxiang Li, Zilei Wang, Yang Deng
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on23
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- The Flan Collection: Designing Data and Methods for Effective Instruction TuningShayne Longpre, Le Hou, Tu Vu, Albert Webson et al.ICML 2023 · 908 citations
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsWeize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang et al.ICLR 2024 · 594 citations
- SOTOPIA: Interactive Evaluation for Social Intelligence in Language AgentsXuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang et al.ICLR 2024 · 288 citations
- Evaluating and Inducing Personality in Pre-trained Language ModelsGuangyuan Jiang, Manjie Xu, Song-Chun Zhu, Wenjuan Han et al.NeurIPS 2023 · 192 citations
Related papers
- Neuron based Personality Trait Induction in Large Language ModelsJia Deng, Tianyi Tang, Yanbin Yin, Wenhao Yang et al.ICLR 2025
- UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical ModulationTianlong Li, Wenhao Liu, Muling Wu, Shihan Dou et al.EMNLP Findings 2025
- PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector AlgebraXiachong Feng, Liang Zhao, Weihong Zhong, Yichong Huang et al.ICLR 2026 · 11 citations
- PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI AssistantsZheng Zhao, Clara Vania, Subhradeep Kayal, Naila Khan et al.ACL Findings 2025 · 9 citations
- BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded DataWenkai Li, Jiarui Liu, Andy Liu, Xuhui Zhou et al.ACL 2025
