Large language models (LLMs) can generate personas based on prompts that describe the target user group. To understand what kind of personas LLMs generate, in this research led by Joni Salminen, we investigate the diversity and bias in 450 LLM-generated personas with the help of internal evaluators (n=4) and subject-matter experts (SMEs) (n=5). The research findings…… Continue reading Deus Ex Machina and Personas from Large Language Models: Investigating the Composition of AI-Generated Persona Descriptions