Steph Buongiorno, PhD, is a postdoctoral research fellow in data science and high-performance computing (HPC) at Emory University’s Department of Data and Decision Sciences. She is also the director of Democracy Lab and the development of the Democracy Viewer. Her transdisciplinary research produces new knowledge that extends beyond the boundaries of any single field by introducing new methods for interpreting texts, data, culture, and society. Her work has been published by Cambridge University Press, AAAI, and IEEE, and supported by the National Science Foundation (NSF), the National Endowment for the Humanities (NEH), and the National Institute of Justice (NIJ). She enjoys poetry, all sorts of sensory things, and quiet underwater worlds.

If my open source software has helped you in some way, consider supporting my work: Buy Me A Coffee

's Picture

Evaluating the Efficacy of LLMs to Emulate Human Personalities for Video Game Play

Evaluating the Efficacy of LLMs to Emulate Human Personalities for Video Game Play

To improve the realism of affective Non-Player Characters (NPCs) in video games, this study investigates whether Large Language Models (LLMs) can emulate human personalities. Using the Big Five framework and over 50,000 responses from the International Personality Item Pool (IPIP), LLMs were prompted with self-assessment items corresponding to various personality profiles. Their outputs were then compared to human baseline responses to evaluate accuracy and consistency. Results showed that while some local models exhibited no alignment with human profiles, certain frontier models achieved high alignment. These findings suggest that LLMs can provide a method for designing NPCs with more realistic, personality-driven behavior.