AI Safety

Designing Safe and Relevant Generative Chats for Math Learning in Intelligent Tutoring Systems

Zachary Levonian, Owen Henkel, Chenglu Li, Millie-Ellen Postle

Journal of Educational Data Mining

More than 8,000 learners used a structured growth-mindset conversation inside a mathematics tutor, giving researchers a practical view of moderation and response quality. Monitoring found no overtly objectionable model outputs, but identified subtler failures to respond appropriately to concerning student messages. A separate study found that educators preferred moderately guided textbook-supported answers. Neither safety monitoring nor response preference establishes improved learning, and both findings depend on the particular system and evaluation context.