The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses
Warsaw University of Technology（华沙理工大学）；University of Warsaw（华沙大学）
Wiktoria Mieleszczenko-Kowszewicz, Dawid Płudowski, Filip Kołodziejczyk, Jakub Świstak, Julian Sienkiewicz, Przemysław Biecek
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.
Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion
School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；National University of Singapore（新加坡国立大学）；Inner Mongolia Research Institute, Shanghai Jiao Tong University（上海交通大学内蒙古研究院）
Evidence of a log scaling law for political persuasion with large language models
University of Oxford（牛津大学）；The Alan Turing Institute（艾伦·图灵研究所）；Royal Holloway, University of London（伦敦大学皇家霍洛威学院）；Bocconi University（博科尼大学）；Meedan（米丹（Meedan））
The Levers of Political Persuasion with Conversational AI
UK AI Security Institute（英国人工智能安全研究所）；University of Oxford（牛津大学）；The London School of Economics and Political Science（伦敦政治经济学院）；Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）
