Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps

no code implementations • 23 Apr 2022 • Oren Barkan, Edan Hauon, Avi Caciularu, Ori Katz, Itzik Malkiel, Omri Armstrong, Noam Koenigstein

Transformer-based language models significantly advanced the state-of-the-art in many linguistic tasks.