Skip to content

AYO: A Safe and Privacy-Preserving Platform for Studying Children's Interactions with LLMs

AYO: A Safe and Privacy-Preserving Platform for Studying Children's Interaction with LLMs

arXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses· arXiv:2611.10054· Huiwen Alex Yang, Rachel Skwersky, Bill D. Thompson, Celeste Kidd·Indexed by this site · 2 days ago· Originally publishedTools
AI summary

The researchers introduce AYO (AI Youth Open Science), an open-source platform for safely and systematically studying children's interactions with conversational AI. The platform provides a child-friendly interface, age-configurable safety guardrails, researcher monitoring, and privacy-preserving data practices, and supports cross-sectional, longitudinal, and experimental studies of how children use and respond to LLMs and how AI design affects developmental aspects such as trust, cognitive judgment, and curiosity. The authors state that this infrastructure can provide evidence for safer AI systems, educational practice, and AI policy for children.

Related events and news

1 events · 0 news mentions

Read originalarxiv.org