As the landscape of artificial intelligence continues to evolve, the need for comprehensive and nuanced evaluation
methods increases as well. Traditional metrics such as accuracy and precision, while important, are insu cient for fully
capturing the complexities and impacts of AI systems.

The SAIL Spring School aims to address this gap by introducing participants to a diverse array of evaluation strategies,
such as user evaluations, ethical and societal impacts, evaluating outcomes that are co-constructed between user and
AI, mathematical guarantees, interpretability and transparency assessments, context-specific metrics, etc.

More information and registration under: https://www.sail.nrw/springschool/