Exploring User Acceptance and Concerns toward LLM-powered Conversational Agents in Immersive Extended Reality

2025-12-17

AI Summary

This study investigates user acceptance of and privacy concerns toward large language model (LLM)-driven conversational agents in immersive extended reality (XR) environments, where natural voice interaction risks inadvertent disclosure of sensitive information and multimodal sensor data fusion exacerbates privacy threats. Method: A large-scale crowdsourced experiment (N = 1,036) systematically examines the three-way interaction among XR scenario type, voice interaction modality, and data processing location. Contribution/Results: We present the first multidimensional user acceptance map for LLM-based conversational agents in XR, revealing counterintuitive findings—including lower acceptance among existing XR device owners, significant gender differences, and heightened sensitivity to location data over other modalities—leading to the “familiarity double-edged sword” theoretical framework. Results further demonstrate that prior generative AI usage significantly increases acceptance. We propose actionable recommendations: transparent communication protocols and tiered data governance mechanisms—both preliminarily adopted by XR platform vendors.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Security and Privacy: Large-scale security measurements

Abstract

The rapid development of generative artificial intelligence (AI) and large language models (LLMs), and the availability of services that make them accessible, have led the general public to begin incorporating them into everyday life. The extended reality (XR) community has also sought to integrate LLMs, particularly in the form of conversational agents, to enhance user experience and task efficiency. When interacting with such conversational agents, users may easily disclose sensitive information due to the naturalistic flow of the conversations, and combining such conversational data with fine-grained sensor data may lead to novel privacy issues. To address these issues, a user-centric understanding of technology acceptance and concerns is essential. Therefore, to this end, we conducted a large-scale crowdsourcing study with 1036 participants, examining user decision-making processes regarding LLM-powered conversational agents in XR, across factors of XR setting type, speech interaction type, and data processing location. We found that while users generally accept these technologies, they express concerns related to security, privacy, social implications, and trust. Our results suggest that familiarity plays a crucial role, as daily generative AI use is associated with greater acceptance. In contrast, previous ownership of XR devices is linked to less acceptance, possibly due to existing familiarity with the settings. We also found that men report higher acceptance with fewer concerns than women. Regarding data type sensitivity, location data elicited the most significant concern, while body temperature and virtual object states were considered least sensitive. Overall, our study highlights the importance of practitioners effectively communicating their measures to users, who may remain distrustful. We conclude with implications and recommendations for LLM-powered XR.

Problem

• Examining user acceptance and concerns about LLM-powered conversational agents in extended reality.
• Investigating privacy risks from combining conversational and sensor data in XR environments.
• Analyzing how factors like XR setting, speech interaction, and data location affect user decisions.

Innovation

• Conducted large-scale crowdsourcing study with 1036 participants
• Examined user decision-making across XR settings and data types
• Analyzed acceptance factors like familiarity, gender, and data sensitivity