Can AI Have a Personality? Prompt Engineering for AI Personality Simulation: A Chatbot Case Study in Gender-Affirming Voice Therapy Training
This work addresses the problem of creating AI with stable personalities for applications like therapy training, though it is incremental as it builds on existing prompt engineering methods.
The study investigated whether large language models can simulate a consistent personality through prompt engineering, using a chatbot for gender-affirming voice therapy training, and found that the chatbot maintained a recognizable persona and distinct personality based on the Big Five Personality test.
This thesis investigates whether large language models (LLMs) can be guided to simulate a consistent personality through prompt engineering. The study explores this concept within the context of a chatbot designed for Speech-Language Pathology (SLP) student training, specifically focused on gender-affirming voice therapy. The chatbot, named Monae Jackson, was created to represent a 32-year-old transgender woman and engage in conversations simulating client-therapist interactions. Findings suggest that with prompt engineering, the chatbot maintained a recognizable and consistent persona and had a distinct personality based on the Big Five Personality test. These results support the idea that prompt engineering can be used to simulate stable personality characteristics in AI chatbots.