AI Seminar: Interpreting Training

Lille UP1, DIKU Lille UP1, DIKU, Universitetsparken 1, 2100 København Ø, København Ø, Denmark

Abstract: Interpretability research in NLP often follows a predictable pattern—pick an indicator of structure or knowledge such as probe or challenge set accuracy, measure that indicator in a fully trained model, and assert that this structure or information is integral to how the model functions. However, we can achieve a much deeper understanding by considering […]