Explanation Multiplicity in SHAP: Characterization and Assessment

arXiv:2601.12654 · cs.LG, cs.AI · Submitted 2026-01-19 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-01-19

Updated: 2026-10-07

Code: https://github.com/Aguno/SHAP_Multiplicity

Project page: https://umangsbhatt.github.io/reports/AAAI_XAI_QB.pdf

Terminology

• Accountability — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes

Sources

• On the Robustness of Interpretability Methods
• Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI
• True to the Model or True to the Data?

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