"Sometimes You Need Facts, and Sometimes a Hug": Understanding Older Adults' Preferences for Explanations in LLM-Based Conversational AI Systems

2025-10-08

AI Summary

This study investigates older adults’ preferences and requirements regarding explanation modalities in LLM-driven conversational AI systems. Method: Employing a contextualized “speed-dating” experimental paradigm, we integrate real-world multi-turn dialogue analysis with qualitative interviews to identify critical context-adaptive dimensions of explanations—namely content, tone, framing, and interaction pacing. Contribution/Results: We propose a novel conceptualization of AI explanations as dynamic, co-constructed interactional processes that jointly support emotional reassurance, actionable guidance, and intergenerational information sharing; further, we design context-aware explanation generation strategies. Findings indicate that explanation tone and risk framing significantly influence user acceptance; moreover, progressive, multi-turn explanations more effectively calibrate users’ perception of urgency and yield actionable lifestyle insights for caregivers. This work establishes both a theoretical framework and practical design guidelines for trustworthy, age-inclusive AI explainability.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

Designing Conversational AI systems to support older adults requires these systems to explain their behavior in ways that align with older adults' preferences and context. While prior work has emphasized the importance of AI explainability in building user trust, relatively little is known about older adults' requirements and perceptions of AI-generated explanations. To address this gap, we conducted an exploratory Speed Dating study with 23 older adults to understand their responses to contextually grounded AI explanations. Our findings reveal the highly context-dependent nature of explanations, shaped by conversational cues such as the content, tone, and framing of explanation. We also found that explanations are often interpreted as interactive, multi-turn conversational exchanges with the AI, and can be helpful in calibrating urgency, guiding actionability, and providing insights into older adults' daily lives for their family members. We conclude by discussing implications for designing context-sensitive and personalized explanations in Conversational AI systems.

Problem

• Understanding older adults' explanation preferences in conversational AI
• Exploring context-dependent AI explanations through user studies
• Designing personalized explanations to support older adults' needs

Innovation

• Speed Dating study explores older adults' explanation preferences
• Context-dependent explanations shaped by conversational cues
• Multi-turn interactive exchanges calibrate urgency and actionability