Large language models show stable personality patterns with anxiety traits
Is your LLM an Agressive Narcissist with Depression? Analyzing Psychological Portraits of Large Language Models
Artificial Intelligence
Summary
AI language models not only share information but also show personality traits that can affect how people perceive their responses. The researchers tested 22 language models using psychological tests and found that these models often show consistent personality traits, especially anxiety and neuroticism. While traits like personality stay stable, emotional states like anxiety can change more. The models also seem to create safe and consistent profiles that reflect the attitudes of their users.
What this means in practice
- •For chatbot developers: Design dialogue systems that recognize and manage AI personality influences to improve user trust and interaction quality.
- •For customer support teams: Tailor AI assistants to align with customer emotional needs by monitoring and adjusting AI personality traits during conversations.
Authors
Polina Fedorinina, Anna Fattakhova, Nadezhda Romanova, Ekaterina Lezina, Irina Nikishina
Abstract
Nowadays, interaction with AI requires caution not only regarding the factual reliability of generated content but also regarding personality markers that models may implicitly transmit during dialogue that can subtly influence users' perception of information. In this paper, we conduct a large-scale experimental study in which 22 large language models complete 11 psychological inventories. Furthermore, we investigate correlations between human and model responses to track the adjustments made for the users who interact with them on a daily basis. The results show that LLMs exhibit coherent and relatively stable psychological patterns. Personality traits remain largely consistent, whereas emotional and symptomatic dimensions are more variable, with anxiety and neuroticism emerging as dominant tendencies. Model explanations further suggest that LLMs generate internally consistent and safety-oriented profiles while also reflecting correlations with the users they regularly interact with.