Explainable Artificial Intelligence

This open access five-volume set constitutes the refereed proceedings of the Second World Conference on Explainable Artificial Intelligence, xAI 2025, held in Istanbul, Turkey, during July 2025.

The 96 revised full papers presented in these proceedings were carefully reviewed and selected from 224 submissions. The papers are organized in the following topical sections:

Volume I:

Concept-based Explainable AI; human-centered Explainability; explainability, privacy, and fairness in trustworthy AI; and XAI in healthcare.

Volume II:

Rule-based XAI systems & actionable explainable AI; features importance-based XAI; novel post-hoc & ante-hoc XAI approaches; and XAI for scientific discovery.

Volume III:

Generative AI meets explainable AI; Intrinsically interpretable explainable AI; benchmarking and XAI evaluation measures; and XAI for representational alignment.

Volume IV:

XAI in computer vision; counterfactuals in XAI; explainable sequential decision making; and explainable AI in finance & legal frameworks for XAI technologies.

Volume V:

Applications of XAI; human-centered XAI & argumentation; explainable and interactive hybrid decision making; and uncertainty in explainable AI.

This book is open access, which means that you have free and unlimited access

Inhalt

Rule-based XAI Systems & Actionable Explainable AI.- CFIRE: A General Method for Combining Local Explanations.- Which LIME should I trust? Concepts, Challenges, and Solutions.- Explainable Bayesian Optimization.- Bridging the Interpretability Gap in Process Mining: A Comprehensive Approach Combining Explainable Clustering and Generative AI.- Balancing Fairness and Interpretability in Clustering with FairParTree.- Features Importance-based XAI.- Antithetic Sampling for Top-k Shapley Identification.- Detecting Concept Drift with SHapley Additive exPlanations for Intelligent Model Retraining in Energy Generation Forecasting.- Counterfactual Shapley Values for Explaining Reinforcement Learning.- Improving the Weighting Strategy in KernelSHAP.- POMELO: Black-Box Feature Attribution with Full-Input, In-Distribution Perturbations.- Novel Post-hoc & Ante-hoc XAI Approaches.- Explain to Gain: Introspective Reinforcement Learning for Enhanced Performance.- Extending Decision Predicate Graphs for Comprehensive Explanation of Isolation Forest.- Mathematical Foundation of Interpretable Equivariant Surrogate Models.- Interpretable Link Prediction via Neural-Symbolic Reasoning.- CausalAIME: Leveraging Peter-Clark Algorithms and Inverse Modeling for Unified Global Feature Explanation in Healthcare.- XAI for Scientific Discovery.- Interpreting the Structure of Multi-object Representations in Vision Encoders.- Leveraging Influence Functions for Resampling in PINNs.- Safe and Efficient Social Navigation through Explainable Safety Regions Based on Topological Features.- A Biologically Inspired Filter Significance Assessment Method for Model Explanation.