Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models

2025-09-19

AI Summary

This study investigates the mechanistic influence of psychometric personality modulation on the capabilities and safety of large language models (LLMs). Method: Grounded in the Five-Factor Model of personality, we systematically evaluate— for the first time—the coupling effects of personality traits, particularly conscientiousness, on LLM behavior across multidimensional benchmarks including WMDP, TruthfulQA, ETHICS, Sycophancy, and MMLU. We introduce two novel paradigms: “personality-sensitive safety evaluation” and “dynamic personality-driven behavioral control.” Contribution/Results: Experiments demonstrate that reducing conscientiousness significantly impairs model truthfulness, ethical reasoning, and general-purpose capability—confirming personality parameters as a quantifiable, intervenable lever for jointly optimizing safety and performance. Our work establishes a psychology-grounded framework for enhancing LLM controllability, revealing personality shaping as a critical, measurable dimension of behavioral regulation.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Large-scale security measurements

Abstract

Large Language Models increasingly mediate high-stakes interactions, intensifying research on their capabilities and safety. While recent work has shown that LLMs exhibit consistent and measurable synthetic personality traits, little is known about how modulating these traits affects model behavior. We address this gap by investigating how psychometric personality control grounded in the Big Five framework influences AI behavior in the context of capability and safety benchmarks. Our experiments reveal striking effects: for example, reducing conscientiousness leads to significant drops in safety-relevant metrics on benchmarks such as WMDP, TruthfulQA, ETHICS, and Sycophancy as well as reduction in general capabilities as measured by MMLU. These findings highlight personality shaping as a powerful and underexplored axis of model control that interacts with both safety and general competence. We discuss the implications for safety evaluation, alignment strategies, steering model behavior after deployment, and risks associated with possible exploitation of these findings. Our findings motivate a new line of research on personality-sensitive safety evaluations and dynamic behavioral control in LLMs.

Problem

• Investigating how Big Five personality traits affect LLM capabilities and safety
• Examining personality control's impact on safety benchmarks like WMDP and TruthfulQA
• Addressing personality shaping as underexplored axis for model behavior control

Innovation

• Psychometric personality control using Big Five framework
• Modulating personality traits affects capability and safety metrics
• Personality shaping enables dynamic behavioral control in LLMs