y0news
← Feed
Back to feed
🧠 AI NeutralImportance 4/10

Knowledge-Based Design Requirements for Generative Social Robots in Higher Education

arXiv – CS AI|Stephan Vonschallen, Dominique Oberle, Theresa Schmiedel, Friederike Eyssel||4 views
🤖AI Summary

Researchers identify 12 knowledge-based design requirements for generative social robots in higher education, categorized into self-knowledge, user-knowledge, and context-knowledge. The study addresses risks like hallucinations and overreliance in AI tutoring systems through interviews with university students and lecturers.

Key Takeaways
  • Generative social robots powered by large language models enable adaptive tutoring but introduce risks including hallucinations, overreliance, and privacy violations.
  • Twelve design requirements were identified across three knowledge types: self-knowledge, user-knowledge, and context-knowledge.
  • The research provides a structured foundation for designing responsible AI tutoring systems in higher education.
  • Current frameworks for educational AI primarily define desired behaviors but rarely specify knowledge prerequisites for reliable operation.
  • The study involved semi-structured interviews with university students and lecturers to identify practical requirements.
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles