The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses

TL;DR

This paper investigates how large language models adapt their linguistic features to influence personality traits, revealing specific patterns and differences across models in personalized persuasive responses based on Big Five traits.

Contribution

It identifies key linguistic features used by LLMs to influence Big Five personality traits and compares their adaptation across different model families.

Findings

Models use anxiety words for neuroticism

Increase achievement words for conscientiousness

Vary in adapting language for openness and neuroticism

Abstract

This study explores how the Large Language Models (LLMs) adjust linguistic features to create personalized persuasive outputs. While research showed that LLMs personalize outputs, a gap remains in understanding the linguistic features of their persuasive capabilities. We identified 13 linguistic features crucial for influencing personalities across different levels of the Big Five model of personality. We analyzed how prompts with personality trait information influenced the output of 19 LLMs across five model families. The findings show that models use more anxiety-related words for neuroticism, increase achievement-related words for conscientiousness, and employ fewer cognitive processes words for openness to experience. Some model families excel at adapting language for openness to experience, others for conscientiousness, while only one model adapts language for neuroticism. Our findings show how LLMs tailor responses based on personality cues in prompts, indicating their potential to create persuasive content affecting the mind and well-being of the recipients.