Paper
Who Explains Privacy Policies to Me? Embodied and Textual LLM-Powered Privacy Assistants in Virtual Reality
Authors
Vincent Freiberger, Moritz Dresch, Florian Alt, Arthur Fleig, Viktorija Paneva
Abstract
Virtual Reality (VR) systems collect fine-grained behavioral and biometric data, yet privacy policies are rarely read or understood due to their complex language, length, and poor integration into users' interaction workflows. To lower the barrier to informed consent at the point of choice, we explore a Large Language Model (LLM)-powered privacy assistant embedded into a VR app store to support privacy-aware app selection. The assistant is realized in two interaction modes: a text-based chat interface and an embodied virtual avatar providing spoken explanations. We report on an exploratory within-subjects study $(N = 21)$ in which participants browsed VR productivity applications under unassisted and assisted conditions. Our findings suggest that both interaction modes support more deliberate engagement with privacy information and decision-making, with privacy scores primarily functioning as a veto mechanism rather than a primary selection driver. The impact of embodied interaction varied between participants, while textual interaction supported reflective review.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.01638v1</id>\n <title>Who Explains Privacy Policies to Me? Embodied and Textual LLM-Powered Privacy Assistants in Virtual Reality</title>\n <updated>2026-03-02T09:13:41Z</updated>\n <link href='https://arxiv.org/abs/2603.01638v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.01638v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Virtual Reality (VR) systems collect fine-grained behavioral and biometric data, yet privacy policies are rarely read or understood due to their complex language, length, and poor integration into users' interaction workflows. To lower the barrier to informed consent at the point of choice, we explore a Large Language Model (LLM)-powered privacy assistant embedded into a VR app store to support privacy-aware app selection. The assistant is realized in two interaction modes: a text-based chat interface and an embodied virtual avatar providing spoken explanations. We report on an exploratory within-subjects study $(N = 21)$ in which participants browsed VR productivity applications under unassisted and assisted conditions. Our findings suggest that both interaction modes support more deliberate engagement with privacy information and decision-making, with privacy scores primarily functioning as a veto mechanism rather than a primary selection driver. The impact of embodied interaction varied between participants, while textual interaction supported reflective review.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n <published>2026-03-02T09:13:41Z</published>\n <arxiv:comment>11 pages, 1 figure, 1 table</arxiv:comment>\n <arxiv:primary_category term='cs.HC'/>\n <author>\n <name>Vincent Freiberger</name>\n </author>\n <author>\n <name>Moritz Dresch</name>\n </author>\n <author>\n <name>Florian Alt</name>\n </author>\n <author>\n <name>Arthur Fleig</name>\n </author>\n <author>\n <name>Viktorija Paneva</name>\n </author>\n <arxiv:doi>10.1145/3772363.3798567</arxiv:doi>\n <link href='https://doi.org/10.1145/3772363.3798567' rel='related' title='doi'/>\n </entry>"
}