SCOPE

In the future people will collaborate more and more with machines to solve complex problems using AI techniques. Such a collaboration requires adequate communication, trust, clarity and understanding.
eXplainalbe AI (XAI) aims at addressing such challenges by combining the best of symbolic AI and Machine Learning including neural models, evolutionary computing and fuzzy systems. Such topic has been studied for years by all different communities of AI, with different definitions, evaluation metrics, motivations and results. In addition to technology, this involves social and legal issues as well as a wide range of real-world applications and domains. Both interpretability by design methods and post-hoc methods for explaining complex models have been proposed and investigated. Research has also redirected its emphasis on the structure of explanations and human-centered Artificial Intelligence, recognizing that the ultimate users of interactive technologies are humans.

This conference aims at attracting different research perspectives to promote debate. It intends to be a major multidisciplinary and interdisciplinary forum, bringing together academics and scholars of different disciplines, interested in the study, analysis, design, modelling and implementation of interpretable and explainable AI systems. Contributions are welcome both in addressing theoretical issues and in a broad range of application fields.

CONFERENCE AREAS

Each of these topic areas is expanded below but the sub-topics list is not exhaustive. Papers may address one or more of the listed sub-topics, although authors should not feel limited by them. Unlisted but related sub-topics are also acceptable, provided they fit in one of the following main topic areas:

1. TECHNOLOGY
2. SOCIAL AND LEGAL ISSUES
3. APPLICATIONS

AREA 1: TECHNOLOGY

Generative AI vs Interpretability
Explainable Generative AI
XAI using Machine Learning
Deep Learning and XAI
Fuzzy Systems and Logic for XAI
Knowledge Graphs in XAI
Explainable Graph Neural Networks
Explainable Neuro-Symbolic Reasoning
Evaluation of Explainability
Argumentative-Based Approaches for XAI
Bayesian Modelling for Interpretability
Explainable Edge Computing
Human-Computer Interfaces Supporting XAI
Natural Language Processing and XAI
XAI for the Semantic Web
Ontologies Supporting XAI
Metrics for Explanations
XAI Benchmarking
Evolutionary XAI Approaches
XAI for Evolutionary Computing
Post-Hoc Methods for Explainability
Model-Specific vs Model-Agnostic Methods for Explainability

AREA 2: SOCIAL AND LEGAL ISSUES

Ethical Concerns of XAI
Accountability and Responsibility
Explainable Bias and Fairness of XAI Systems
Model Accuracy and Interpretability
Explainability Pitfalls and Problems in XAI
Prevention/Detection of Deceptive AI Explanations
Social Implications of Synthetic Explanations
Trust Management and Reputation
Regulatory Compliance
Adversarial Attacks Explanations

AREA 3: APPLICATIONS

Healthcare and Biomedical Sciences
Human/AI Cooperation
Decision-Support Systems
Recommender Systems
Computer Vision Applications
Robotics and Control Systems
Explaining Object and Obstacle Detection
Explainable Methods for Finance
Explaining Project Risk
Explainability in Transportation Systems
Supply Chains and Industry 4.0
Internet of Things
Security and Privacy
Privacy-Preserving Systems