Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation

G Amir, S Bassan, G Katz - arxiv preprint arxiv:2408.03915, 2024 - arxiv.org
The ability to interpret Machine Learning (ML) models is becoming increasingly essential.
However, despite significant progress in the field, there remains a lack of rigorous …

[PDF][PDF] Bridging the Gap Between Black Box AI and Clinical Practice: Advancing Explainable AI for Trust, Ethics, and Personalized Healthcare Diagnostics

DA Tuan - 2024 - preprints.org
Explainable AI (XAI) has emerged as a pivotal tool in healthcare diagnostics, offering much-
needed transparency and interpretability in complex AI models. XAI techniques, such as …

Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons

S Bassan, S Gur, R Eliav - arxiv preprint arxiv:2502.03391, 2025 - arxiv.org
Minimal sufficient reasons represent a prevalent form of explanation-the smallest subset of
input features which, when held constant at their corresponding values, ensure that the …

A Joint Learning Framework for Bridging Defect Prediction and Interpretation

G Xu, Z Zhu, X Guo, W Wang - arxiv preprint arxiv:2502.16429, 2025 - arxiv.org
Over the past fifty years, numerous software defect prediction (SDP) approaches have been
proposed. However, the ability to explain why predictors make certain predictions remains …

On the Complexity of Global Necessary Reasons to Explain Classification

M Calautti, E Malizia, C Molinaro - arxiv preprint arxiv:2501.06766, 2025 - arxiv.org
Explainable AI has garnered considerable attention in recent years, as understanding the
reasons behind decisions or predictions made by AI systems is crucial for their successful …