What question did this study set out to answer?

This research aims to explore how large language models can simulate user research using synthetic participants in augmented reality design.

July 4, 2026

Can LLM-driven synthetic participants help user research? A case study in designing augmented reality for education

SXSuyi XuUniversity of Bath RRRafael RobertoServiço Nacional de Aprendizagem Industrial MSManoela SilvaUniversidade de Pernambuco

Key Points

This research aims to explore how large language models can simulate user research using synthetic participants in augmented reality design.
Developed a workflow using large language models to simulate user research with synthetic participants.
Evaluated the plausibility of open-ended responses compared to human responses in augmented reality design.
Conducted a case study focusing on educational applications of augmented reality.
Synthetic participants provided plausible and comprehensive open-ended responses, but diverged from human responses on semi-open and closed items.
SPs were noted to enhance early qualitative insights in the design process.
While useful, SPs cannot fully substitute for human studies in user research.

Abstract

ABSTRACT: Conventional user research with human participants faces significant challenges, including substantial time and resource requirements, and limited scalability. In response, this study presents an efficient, cost-effective workflow driven by large language models (LLMs) for simulating user research with synthetic participants (SPs) at scale. In a case study in design augmented reality for education, SPs’ open-ended answers were plausible and comprehensive, yet semi-open and closed items diverged from those of humans. SPs can augment early qualitative work, but cannot replace human studies.

Ask AI

Helpful

Bookmark

View Full Paper