arXiv:2507.01548v3 Announce Type: replace-cross Abstract: This paper explores how older migrants in urban China can record stories that everyday language and design often miss. We ran two co-creation workshops with 10 elders. Activities combined oral storytelling, facilitator-mediated AI assistance, and hand-making. Large language models proposed candidate glyphs through a facilitator. Participants crafted new Hanzi to hold their stories. The resulting characters served as memory anchors for later sharing and retelling. Our interpretive analysis shows heterogeneity and adaptive capacity among
The increasing accessibility and capability of large language models are enabling novel applications outside of traditional tech sectors. This occurs as an aging global population seeks new forms of engagement and cultural preservation.
This research provides a practical example of how AI can be leveraged for cultural preservation, intergenerational engagement, and cognitive support, particularly within aging populations. It demonstrates AI's potential in facilitating creative expression and documenting personal histories.
AI tools are not just for high-tech industries or efficiency gains; they are becoming instruments for humanistic and community-based projects, changing the perception of AI from purely technical to socially integrative.
- · AI developers focused on culturally specific applications
- · Elderly care and community organizations
- · Linguistics and anthropology researchers
- · Traditional, non-adaptive memory preservation methods
AI-assisted cultural preservation techniques gain traction, leading to more projects documenting diverse human experiences.
Development of specialized AI models tailored for linguistic nuances and cultural contexts becomes a growth area within AI research and application.
These tools become integrated into educational curricula and social welfare programs, fostering intergenerational understanding and cognitive health.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI