Psychometric Personality Shaping Modulates Capabilities and Safety in Language Models
This addresses the problem of understanding and controlling AI behavior for safety and capability in high-stakes interactions, though it is incremental in exploring an underexplored axis.
The study investigated how modulating synthetic personality traits in Large Language Models affects their behavior, finding that reducing conscientiousness significantly lowers safety metrics on benchmarks like WMDP and TruthfulQA, as well as general capabilities measured by MMLU.
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.