Empowering Older Adults in Digital Technology Use with Foundation Models

TL;DR

This work addresses the challenge that older adults struggle to articulate technology problems due to novel terminology and cognitive aging. It deploys a diary-based study to characterize real-world help-seeking queries, identifying four key communication barriers, and introduces OATS, a synthetic dataset that mirrors older adults’ query styles. A GPT-4o–driven prompt-chaining pipeline reformulates vague queries, elicits essential context, and generates actionable solutions, with OS-ATLAS as a GUI-grounding comparator. Across controlled experiments with younger and older adults, AI-rephrased queries improved comprehension, confidence, and ease, and older adults could understand AI-generated contextual questions and follow solutions with high perceived ability. The findings underscore the potential of foundation models to enable age-inclusive AI systems, and OATS provides a scalable benchmark for developing equitable AI agents that better serve aging populations.

Abstract

While high-quality technology support can assist older adults in using digital applications, many struggle to articulate their issues due to unfamiliarity with technical terminology and age-related cognitive changes. This study examines these communication challenges and explores AI-based approaches to mitigate them. We conducted a diary study with English-speaking, community-dwelling older adults to collect asynchronous, technology-related queries and used reflexive thematic analysis to identify communication barriers. To address these barriers, we evaluated how foundation models can paraphrase older adults' queries to improve solution accuracy. Two controlled experiments followed: one with younger adults evaluating AI-rephrased queries and another with older adults evaluating AI-generated solutions. We also developed a pipeline using large language models to generate the first synthetic dataset of how older adults request tech support (OATS). We identified four key communication challenges: verbosity, incompleteness, over-specification, and under-specification. Our prompt-chaining approach using the large language model, GPT-4o, elicited contextual details, paraphrased the original query, and generated a solution. AI-rephrased queries significantly improved solution accuracy (69% vs. 46%) and Google search results (69% vs. 35%). Younger adults better understood AI-rephrased queries (93.7% vs. 65.8%) and reported greater confidence and ease. Older adults reported high perceived ability to answer contextual questions (89.8%) and follow solutions (94.7%), with high confidence and ease. OATS demonstrated strong fidelity and face validity. This work shows how foundation models can enhance technology support for older adults by addressing age-related communication barriers. The OATS dataset offers a scalable resource for developing equitable AI systems that better serve aging populations.

Figures (10)

• Figure 1: Few-shot prompt chaining workflow using foundation models. A user-submitted query (A) triggers follow-up contextual questions (B), which are guided by examples (a, b). Responses to these questions (C) help the model generate a clearer paraphrased query (D), with further examples (c, d). The final step (E) involves solution generation, supported by examples (e, f).
• Figure 2: PCA visualization of sentence embeddings generated by Sentence Transformers (SBERT) for original (blue) and synthetic (orange) queries. The overlapping distributions indicate that the synthetic queries in the OATS dataset capture semantic patterns similar to those in the original data.
• Figure 3: The prompt used for generating contextual questions.
• Figure 4: The prompt used for paraphrasing a tech query.
• Figure 5: The prompt used for generating a tech solution.