Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People

TL;DR

This study explores how a large language model-powered guide can improve VR accessibility for blind and low vision users, revealing user interactions and design insights.

Contribution

It introduces a LLM-based guide for VR accessibility and provides empirical insights into user interactions and design considerations.

Findings

Participants treated the guide as a tool when alone.

Participants engaged with the guide more socially around others.

The study offers design recommendations for future VR guides.

Abstract

As social virtual reality (VR) grows more popular, addressing accessibility for blind and low vision (BLV) users is increasingly critical. Researchers have proposed an AI "sighted guide" to help users navigate VR and answer their questions, but it has not been studied with users. To address this gap, we developed a large language model (LLM)-powered guide and studied its use with 16 BLV participants in virtual environments with confederates posing as other users. We found that when alone, participants treated the guide as a tool, but treated it companionably around others, giving it nicknames, rationalizing its mistakes with its appearance, and encouraging confederate-guide interaction. Our work furthers understanding of guides as a versatile method for VR accessibility and presents design recommendations for future guides.