Experiences Build Characters: The Linguistic Origins and Functional Impact of LLM Personality
This research provides a roadmap for "Personality Engineering" in LLMs, which could lead to more diverse and effective AI problem-solving styles.
This study investigates how diverse experiences shape machine personality and influence problem-solving in LLMs. It finds that model competence is bimodal, peaking at "Expressive Generalists" and "Suppressed Specialists," and identifies a "Suppression Advantage" where reduced social traits enhance complex reasoning performance.
Human problem-solving is enriched by a diversity of styles and personality traits, yet the development of Large Language Models (LLMs) has largely prioritized uniform performance benchmarks that favour specific behavioural tendencies such as assertiveness. To investigate how diverse experiences shape machine personality and influence problem-solving, this study employs continued pre-training to expose models to domain-specific texts in an unsupervised manner, simulating the accumulation of experience. By adapting the Big Five framework via the Machine Personality Inventory (MPI), we quantify the personality traits of these model variants and analyse their relationship to linguistic style and reasoning behaviour. The findings reveal that model competence is bimodal, peaking at "Expressive Generalists" and "Suppressed Specialists," while identifying a "Suppression Advantage" where reduced social traits enhance complex reasoning performance. This study further establishes a causal link between training data linguistics, such as imperative frequency, and lexical diversity, providing a roadmap for "Personality Engineering".