Post #1817058

SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems https://arxiv.org/abs/2603.17373 "the primary risk is not toxic content but the quiet erosion of learning through answer over-disclosure, misconception reinforcement, and the abdication of scaffolding" "We uncover that all models show broad harm; scale doesn't reliably help; and multi-turn dialogue worsens behavior, with pedagogical failures rising from 17.7% to 77.8%." #AIEd #EdTech