Workshop · Dec 12, 2026
Can We Trust AI Evaluation? Robustness, Causality, and Risk in Modern AI Assessment
Sydney, Australia
We use cookies for analytics.
Workshop
Aashiq Muhamed, Andrew Strait, Ashia Wilson and 4 more
Researchers and child-protection practitioners examine how to assess AI systems used by or affecting children. The workshop considers risks to well-being, evaluation with restricted access to sensitive data, and how to validate protections with the people responsible for children’s safety.
C211-213, Atlanta, Georgia, United States
Conference on Neural Information Processing Systems (NeurIPS)
Host
Workshop · Dec 12, 2026
Sydney, Australia
Seminar · Dec 2, 2026
King’s College London