This study investigates how large language models (LLMs) can support informal learning in social reading environments. Focusing on critical thinking, collaborative knowledge construction, and group learning, it adopts a stage-based co-design approach grounded in an informal learning cycle. Two participatory design workshops were conducted with social readers, LLM experts, and interaction designers. Participants used first-person narratives and shared tasks to envision LLM-assisted learning processes. Thematic and visual analyses revealed three key design principles: stage-specific intervention, bidirectional prompting, and balancing individual autonomy with collaborative engagement. Building on these findings, we propose a conceptual design model illustrating how LLMs can facilitate social learning in future reading platforms. The study contributes to HCI by expanding the theoretical application of informal learning with LLMs, introducing a novel participatory method, and offering actionable insights for the development of AI-mediated social reading tools.
Research Article
Open Access