Personality as Relational Infrastructure: User Perceptions of Personality-Trait-Infused LLM Messaging

Researchers studied how personality-trait-infused LLM messaging affects user perceptions in behavior change systems. The study found that personality-based personalization works through aggregate exposure patterns rather than individual message optimization, with users rating personality-informed messages as more personalized and appropriate.

• →Personality-infused LLM messages showed no improvement at the individual message level but improved overall user perceptions through cumulative exposure.
• →Users who received higher proportions of personality-informed messages rated them as more personalized, appropriate, and reported less negative affect.
• →Four LLM strategies were tested: baseline prompting, few-shot prompting, fine-tuned models, and retrieval augmented generation with Big Five Personality Traits.
• →The research suggests behavior change AI systems should focus on aggregate exposure patterns rather than per-message optimization.
• →Real-world longitudinal studies are needed to validate these findings in practical human-AI interaction contexts.