This repository is a code supplement to the following paper:
Hubert Baniecki, Przemyslaw Biecek, Fabian Fumagalli. The Metagame of Interpretability and Meta-Attributions. NeurIPS 2026
TL;DR: We introduce meta-attributions, which decompose any feature attribution into directional interactions via Shapley values, and we apply them to interpret language and multimodal transformers.
