AI Evaluation Workshop

​🤖 AI Evaluation Workshop: Can We Trust AI for Policy Work? 🔍

​AI tools are increasingly being used to research policy issues, analyse regulations, and support decision-making. But how do we know whether their outputs are accurate, reliable, and useful for real-world policy work?

​Join the HAIPI for an interactive workshop exploring how AI models are evaluated, what existing benchmarks can tell us, and why assessing AI for policy work comes with unique challenges.

​The workshop will be led by Robert Scholz: AI Research Engineer at Ellamind, PhD from Max Planck, and former European Commission consultant.

​No technical expertise is required — just an interest in AI and its implications for policymaking!

​We look forward to seeing you there! ✨