Authors

Steve Azzolin

Publications 2

Preprint Open access

When Are Concept Bottleneck Model Explanations Faithful and Compact?

Stefano Teso, Emanuele Marconato, Steve Azzolin et al. · 2026

Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and debugging. However, their explanations are often derived heuristically. Building on formal explainability, we argue they should also be faithful, i.e., …

Preprint Open access

Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark

Steve Azzolin, Francesco Paolo Nerini, Stefano Teso et al. · 2026

Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined ground truth, such as a motif planted in the data. This protocol implicitly assumes that a GNN trained on such data relies on the intended motif. Although prior work has quest …

Co-authors