Research

Paper

AI LLM March 10, 2026

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

Authors

Jazmin Collins, Sharon Y Lin, Tianqi Liu, Andrea Stevenson Won, Shiri Azenkot

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.

Metadata

arXiv ID: 2603.09964
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09964v1</id>\n    <title>Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People</title>\n    <updated>2026-03-10T17:56:57Z</updated>\n    <link href='https://arxiv.org/abs/2603.09964v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09964v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.ET'/>\n    <published>2026-03-10T17:56:57Z</published>\n    <arxiv:comment>16 pages, 5 figures, 3 tables, Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26), April 13-17, 2026, Barcelona, Spain. ACM</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Jazmin Collins</name>\n    </author>\n    <author>\n      <name>Sharon Y Lin</name>\n    </author>\n    <author>\n      <name>Tianqi Liu</name>\n    </author>\n    <author>\n      <name>Andrea Stevenson Won</name>\n    </author>\n    <author>\n      <name>Shiri Azenkot</name>\n    </author>\n    <arxiv:doi>10.1145/3772318.3791143</arxiv:doi>\n    <link href='https://doi.org/10.1145/3772318.3791143' rel='related' title='doi'/>\n  </entry>"
}