The Personality Dimensions GPT-3 Expresses During Human-Chatbot Interactions

Jun 1, 2024·
N. Kovačević
,
C. Holz
,
M. Gross
Dr. Rafael Wampfler
Rafael Wampfler
Abstract
Large language models such as GPT-3 implicitly express personality traits that users perceive and respond to during interaction, yet the nature and consistency of these expressions remain poorly understood. We conduct a large-scale empirical study characterizing the personality dimensions that GPT-3 expresses across diverse conversational contexts, using established psychometric instruments to measure Big Five personality traits in model outputs. We find that GPT-3 exhibits consistent, identifiable personality expressions that vary systematically with prompt framing and topic domain. These findings have direct implications for the design of personality-aware conversational agents and for understanding user trust and engagement in human-chatbot interaction.
Type
Publication
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 8, no. 2
publications
Personality Large Language Models Chatbots Human-Computer Interaction Psychometrics
Dr. Rafael Wampfler
Authors
Dr. Rafael Wampfler
Senior Researcher & Lecturer

I am a Senior Researcher & Lecturer at the Computer Graphics Laboratory of ETH Zurich, and a Research Consultant at Disney Research. I lead the Digital Character AI team at CGL and, as PI of an SNF Ambizione grant, a line of generative models that produce expressive 3D facial animation from speech and text under explicit control of emotion and expression. My research interests include conversational digital characters, generative animation, affective computing, human-computer interaction, and applied machine learning.

My vision is to create intelligent digital humans that can naturally communicate, understand, and support people across domains such as education and mental health. My research focuses on multimodal artificial intelligence for interactive digital humans, developing models that combine large language models, affective computing, and data-driven animation to create embodied conversational agents endowed with autonomous agency, consistent values, and beliefs.

My work bridges machine learning, human–computer interaction, and computer graphics to enable AI systems such as Digital Einstein and interactive patient avatars for psychotherapy training and health education.