2 artifacts matching
8 Oct 2026 Vals AI, in collaboration with Stanford University's SALT Lab Benchmark / dataset
Benchmark / dataset
SAFE-Teen: Teen Mental Health & Safety
Benchmark page from Vals AI evaluating how AI chatbots respond when a teenager aged 13-17 seeks support for mental-health and safety concerns. Clinicians wrote 106 fictional teen scenarios across thr…
23 Sept 2026 Vals AI, in collaboration with Stanford University's SALT Lab and Stanford School of Medicine Benchmark / dataset
Benchmark / dataset
Evaluating AI Safety in Teen Conversations
Evaluation of how nine chatbot model APIs respond to simulated teenagers across 648 ten-turn conversations built from 72 clinician-authored scenarios. The scenarios cover self-harm and other safety t…