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

TL;DR

This paper investigates how embodied and textual LLM-powered privacy assistants in VR can improve user understanding and engagement with privacy policies during app selection, addressing the complexity and poor integration of policies.

Contribution

It introduces and evaluates two interaction modes of an LLM-powered privacy assistant in VR, demonstrating their effects on user engagement and decision-making.

Findings

Both interaction modes promote more deliberate privacy engagement.

Privacy scores act mainly as veto mechanisms, not primary drivers.

Embodied interaction effects vary among users.

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.