Knowing Ourselves Through Others: Reflecting with AI in Digital Human Debates

2025-11-17

AI Summary

Adolescents’ generative AI literacy is hindered by underdeveloped reflective capacity. Method: This study proposes the “co-reflecting with AI” paradigm, positioning personalized digital humans—as mirror-like agents situated between self and other—to stimulate deep reflection on users’ cognition and values through autonomous, dialogic debate. Leveraging prompt engineering and retrieval-augmented generation (RAG), we designed adaptive digital humans tailored to individual characteristics and conducted empirical inquiry via Research Through Design. Contribution/Results: Participants demonstrated significantly enhanced understanding of generative AI’s capabilities, limitations, and operational logic. More critically, they cultivated a novel form of generative AI literacy centered on critical reflection—validating digital humans as effective and innovative reflective mediators in adolescent AI education.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Philosophy and Ethics of AI: Artificial General Intelligence
• Intelligent Robots: Embodied AI

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

LLMs can act as an impartial other, drawing on vast knowledge, or as personalized self-reflecting user prompts. These personalized LLMs, or Digital Humans, occupy an intermediate position between self and other. This research explores the dynamic of self and other mediated by these Digital Humans. Using a Research Through Design approach, nine junior and senior high school students, working in teams, designed Digital Humans and had them debate. Each team built a unique Digital Human using prompt engineering and RAG, then observed their autonomous debates. Findings from generative AI literacy tests, interviews, and log analysis revealed that participants deepened their understanding of AI's capabilities. Furthermore, experiencing their own creations as others prompted a reflective attitude, enabling them to objectively view their own cognition and values. We propose "Reflecting with AI" - using AI to re-examine the self - as a new generative AI literacy, complementing the conventional understanding, applying, criticism and ethics.

Problem

• Exploring self-other dynamics through AI-mediated Digital Humans
• Developing reflective AI literacy via personalized LLM debates
• Using autonomous AI debates to objectively examine cognition

Innovation

• Using AI as impartial debate partners
• Creating personalized Digital Humans via prompts
• Employing RAG and prompt engineering techniques