Beyond Static Personas: Situational Personality Steering for Large Language Models

• URL: http://arxiv.org/abs/2604.13846v3
• Date: Fri, 17 Apr 2026 08:59:58 GMT
• Title: Beyond Static Personas: Situational Personality Steering for Large Language Models
• Abstract summary: We propose IRIS, a training-free, neuron-based Identify-Retrieve-Steer framework for advanced situational personality steering.<n>Our approach comprises situational persona neuron identification, situation-aware neuron retrieval, and similarity-weighted steering.<n>We empirically validate our framework on PersonalityBench and our newly introduced SPBench, a comprehensive situational personality benchmark.
• Score: 52.33369223308941
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 PersonalityBench 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.

Related papers

• Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models [24.456367163695962]
  This paper introduces explicit personality conditioning in Multimodal Large Language Models (MLLMs)<n>It establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching.<n>Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning.
  arXiv  Detail & Related papers  (2026-06-09T16:34:37Z)
• Experiences Build Characters: The Linguistic Origins and Functional Impact of LLM Personality [10.56924140369377]
  This study employs continued pre-training to expose models to domain-specific texts in an unsupervised manner.<n>We quantify the personality traits of model variants and analyse their relationship to linguistic style and reasoning behaviour.<n>The findings reveal that model competence is bimodal, peaking at "Expressive Generalists" and "Suppressed Specialists"
  arXiv  Detail & Related papers  (2026-03-06T09:42:41Z)
• HUMANLLM: Benchmarking and Reinforcing LLM Anthropomorphism via Human Cognitive Patterns [59.17423586203706]
  We present HUMANLLM, a framework treating psychological patterns as interacting causal forces.<n>We construct 244 patterns from 12,000 academic papers and synthesize 11,359 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.<n>Our dual-level checklists evaluate both individual pattern fidelity and emergent multi-pattern dynamics, achieving strong human alignment.
  arXiv  Detail & Related papers  (2026-01-15T08:56:53Z)
• Structured Personality Control and Adaptation for LLM Agents [11.050618253938126]
  Large Language Models (LLMs) are increasingly shaping human-computer interaction (HCI)<n>We present a framework that models LLM personality via Jungian psychological types.<n>This design allows the agent to maintain nuanced traits while dynamically adjusting to interaction demands.
  arXiv  Detail & Related papers  (2026-01-15T03:15:24Z)
• PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems [30.449659477704543]
  We introduce PTCBENCH, a benchmark designed to quantify the consistency of large language models (LLMs) personalities under controlled situational contexts.<n> PTCBENCH subjects models to 12 distinct external conditions spanning diverse location contexts and life events, and rigorously assesses the personality using the NEO Five-Factor Inventory.<n>Our study on 39,240 personality trait records reveals that certain external scenarios can trigger significant personality changes of LLMs, and even alter their reasoning capabilities.
  arXiv  Detail & Related papers  (2026-01-12T18:15:50Z)
• DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios [57.327907850766785]
  characterization of deception across realistic real-world scenarios remains underexplored.<n>We establish DeceptionBench, the first benchmark that systematically evaluates how deceptive tendencies manifest across different domains.<n>On the intrinsic dimension, we explore whether models exhibit self-interested egoistic tendencies or sycophantic behaviors that prioritize user appeasement.<n>We incorporate sustained multi-turn interaction loops to construct a more realistic simulation of real-world feedback dynamics.
  arXiv  Detail & Related papers  (2025-10-17T10:14:26Z)
• IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization [66.6349183886101]
  We propose IROTE, a novel in-context method for stable and transferable trait elicitation.<n>We show that one single IROTE-generated self-reflection can induce LLMs' stable impersonation of the target trait across diverse downstream tasks.
  arXiv  Detail & Related papers  (2025-08-12T08:04:28Z)
• A Comparative Study of Large Language Models and Human Personality Traits [6.354326674890978]
  Large Language Models (LLMs) have demonstrated human-like capabilities in language comprehension and generation.<n>This study investigates whether LLMs exhibit personality-like traits and how these traits compare with human personality.
  arXiv  Detail & Related papers  (2025-05-01T15:10:15Z)
• Neuron-based Personality Trait Induction in Large Language Models [115.08894603023712]
  Large language models (LLMs) have become increasingly proficient at simulating various personality traits. We present a neuron-based approach for personality trait induction in LLMs.
  arXiv  Detail & Related papers  (2024-10-16T07:47:45Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, a framework for better data construction and model tuning.<n>For insufficient data usage, we incorporate strategies such as Chain-of-Thought prompting and anti-induction.<n>For rigid behavior patterns, we design the tuning process and introduce automated DPO to enhance the specificity and dynamism of the models' personalities.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.