Buch, Englisch, 480 Seiten, Format (B × H): 155 mm x 235 mm
4th World Conference, xAI 2026, Fortaleza, Brazil, July 1–3, 2026, Proceedings, Part IV
Buch, Englisch, 480 Seiten, Format (B × H): 155 mm x 235 mm
Reihe: Communications in Computer and Information Science
ISBN: 978-3-032-45475-1
Verlag: Springer
This open access four-volume set constitutes the refereed proceedings of the Fourth World Conference on Explainable Artificial Intelligence, xAI 2026, held in Fortaleza, Brazil, during July 1–3, 2026.
The 95 revised full papers presented in these proceedings were carefully reviewed and selected from 235 submissions. The papers are organized in the following topical sections:
Volume I: Enhancing Models with XAI: Debugging, Modification, Evaluation; Human-Centred Explanation Systems & Explanation User Interfaces; Rule-Based Explainable AI; Uncertainty-Aware Explainable AI; xAI in Healthcare: Balancing Accuracy, Trust, and Ethics.
Volume II: XAI for Time Series; Trust Through Transparency: Next-Generation Explainable AI in Medicine; Explainable AI for Sequential Decision Making; Mechanistic Interpretability in Explainable AI; XAI and the Physical Sciences.
Volume III: Psychometric Applications for XAI and attribution techniques; Neural-Symbolic Methods for Interpretable and explainable AI; Argumentation, abduction, abstraction and agreement for XAI; Shapley-driven explainable AI; Explainable AI in legal and regulatory contexts.
Volume IV: Counterfactual-based explainable AI; Explainability with and for Large Language Models; Notions and metrics for explainable AI; Contrastive-based explainable AI; Novel approaches and methods for XAI.
Zielgruppe
Research
Autoren/Hrsg.
Fachgebiete
- Mathematik | Informatik EDV | Informatik Technische Informatik Netzwerk-Hardware
- Mathematik | Informatik EDV | Informatik Angewandte Informatik
- Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
- Mathematik | Informatik EDV | Informatik Informatik Natürliche Sprachen & Maschinelle Übersetzung
Weitere Infos & Material
.- Counterfactual-based explainable AI.
.- Model-Centric Counterfactual Explanations via Decision Predicate Graphs.
.- Do Metrics for Counterfactual Explanations Align with User Perception?
.- Concept-based Visual Counterfactual Explanations with Diffusion Models.
.- Evaluating Counterfactual Explanation Methods on Incomplete Inputs.
.- DICE_GI Diversified Counterfactual Explanations for a Group of Instances.
.- Explainability with and for Large Language Models.
.- Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models.
.- Understanding the LLM Black Box: Leveraging Co-Activation and Knowledge Graph for Transparent Skill Inference.
.- Towards Decoding Grammar Perception: Identifying Specialized Neurons in LLMs.
.- Toward Explanations for Causal Reasoning in LLMs: Extending CLadder with Robust Graph-Extraction Evaluation.
.- Notions and metrics for explainable AI.
.- Explainability Metrics for Object Detection Models.
.- Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization.
.- Structural Compactness as a Complementary Criterion for Explanation Quality.
.- An Empirical Study on the Robustness of Local Explanation Methods.
.- Introducing Binomial Stability: A Computational Efficient Approach to Measure Stability in Explainable AI.
.- Contrastive-based explainable AI.
.- MOOPE: Multi-Objective Optimization of Performance and Explainability Through Contrastive Loss.
.- Contrastive Multiclass Explanations: Exploring the Helpfulness of Class-Wise Relevance-Based Explanations.
.- TACENR: Task-Agnostic Contrastive Explanations for Node Representations.
.- Rethinking Explanations: Formalizing Contrast in Description Logics.
.- Novel approaches and methods for XAI.
.- Predicting Explainability in Clustering Algorithms: A Meta-Learning-Based Approach.
.- TabSCM: A practical Framework for Generating Realistic Tabular Data.
.- Scaling the Explanation of Multi-Class Bayesian Network Classifiers.
.- This looks like what? Challenges and Future Research Directions for Part-Prototype Models.
.- eXProj: Explaining Shared Predictive Structure in Multi-Output Models.
