Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Who Explains Privacy Policies to Me? Embodied and Textual LLM-Powered Privacy Assistants in Virtual Reality

Vincent Freiberger, Moritz Dresch, Florian Alt, Arthur Fleig, Viktorija Paneva

TL;DR

A Large Language Model-powered privacy assistant embedded into a VR app store to support privacy-aware app selection and suggests that both interaction modes support more deliberate engagement with privacy information and decision-making.

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.

Who Explains Privacy Policies to Me? Embodied and Textual LLM-Powered Privacy Assistants in Virtual Reality

TL;DR

A Large Language Model-powered privacy assistant embedded into a VR app store to support privacy-aware app selection and suggests that both interaction modes support more deliberate engagement with privacy information and decision-making.

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 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.
Paper Structure (14 sections, 1 figure, 1 table)

This paper contains 14 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Design
  4. User Study
  5. Results
  6. Discussion
  7. Conclusion
  8. Applications Used in the Study
  9. Prompting
  10. Dashboard Data
  11. Prompting Approach for Chat Interface
  12. Prompting Approach for Avatar
  13. Prompting Approach for our Suggested Question Generation
  14. Interview Guide

Figures (1)

  • Figure 1: Illustration of the three VR interface conditions used in the user study. (a) Baseline: storefront-only app store view (b) Chat condition: text-based interface and privacy ratings. (c) Avatar condition: spoken explanations, gesture cues and privacy ratings.