Challenges and Opportunities of LLM-Based Synthetic Personae and Data in HCI
Mirjana Prpa, Giovanni Maria Troiano, Matthew Wood, Yvonne Coady
Abstract
Synthetic personae and data powered by artificial intelligence (AI) are emerging in many HCI areas, including education and training, gaming, and piloting research studies. Recently, Large Language Models (LLMs) have shown promise for synthetic AI personae, experimenting with human and social simulacra and producing synthetic data. This presents challenges and opportunities for extending HCI research via LLMs and AI. In this proposed workshop, we engage HCI researchers interested in working with LLMs, synthetic personae, and synthetic data through speculative design and producing visions, desiderata, and requirements for future HCI research engaging with synthetic personae/data. The outcomes of this workshop may be disseminated to the HCI community through scientific publications or special issues to facilitate continued discussion and advance knowledge on a timely HCI topic.