Answers are grounded in this paper and cite their sources.
As large language models (LLMs) are increasingly integrated into smart home assistants (SHAs), voice interactions are moving beyond constrained commands toward open-ended conversations, increasing ambiguity in user requests. Therefore, this study investigates how request ambiguity and response explainability affect users’ perceived trust, satisfaction, and pleasure in the context of LLM-based smart home assistant (SHA). A 2 × 2 between-subjects experiment was conducted with 211 participants across three scenarios: device control, information inquiry, and schedule planning. Results showed that request ambiguity negatively affected all three outcomes under low explainability. LLM response explainability substantially improved users’ evaluations of trust, satisfaction, and pleasure under high ambiguity, mitigating the negative effects by clarifying how the assistant interpreted user intent and why it generated a particular response. These findings advance understanding of ambiguity and explainability in human–AI interaction from a user experience perspective and highlight the importance of adaptive explanation strategies in LLM-based SHAs.
No takes yet. Share an insight, caveat, or question.
Cui et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: