We Need Explanation Cards to Connect Explanation Algorithms to the Real World

arXiv:2606.16786 · cs.LG · Submitted 2026-06-15 · Read on arXiv

cs.LG

Submitted: 2026-06-15

Updated: 2026-10-06

Terminology

• Explainability — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Automated Test Generation to Detect Individual Discrimination in AI Models
• True to the Model or True to the Data?
• Shapley explainability on the data manifold
• Effector: A Python package for regional explanations
• Informative Post-Hoc Explanations Only Exist for Simple Functions
• The Inadequacy of Shapley Values for Explainability
• Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
• Performative Validity of Recourse Explanations
• The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective
• Human-Centered Explainable AI (XAI): From Algorithms to User Experiences
• Consistent Individualized Feature Attribution for Tree Ensembles

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks