Workshop Details

XAI.it brings together researchers, practitioners, and industry stakeholders interested in the next generation of explainable artificial intelligence. The workshop focuses on the challenges and opportunities introduced by generative models and agentic systems, with particular attention to how transparency, interpretability, and human oversight can support the development of AI that is trustworthy, accountable, and aligned with human values. As AI systems become increasingly autonomous, interactive, and capable of complex decision-making, explainability is no longer only a desirable feature, but a fundamental requirement for responsible adoption. The workshop aims to foster discussion on methods, frameworks, and applications that make generative and agentic AI more understandable, controllable, and reliable across diverse domains. Topics of interest include, but are not limited to, explainability techniques for large language models and foundation models, interpretable reasoning and planning in agentic systems, human-in-the-loop and human-on-the-loop approaches, evaluation of trust and transparency, fairness and accountability, safety and governance, and real-world applications of explainable generative and autonomous AI. The workshop encourages interdisciplinary contributions that bridge technical advances with human-centered, ethical, and regulatory perspectives.



Topics of interests include but are not limited to:

- Explainable AI, GenAI and Agentic AI

- Trustable and Transparent AI, GenAI and Agentic Models

- Justification Models in AI, GenAI and Agentic AI

- Interpretable Machine Learning Models

- Strategies to Explain Black Box Decision Systems

- Designing new Explanation Styles and Approaches

- Evaluating Transparency and Interpretability of AI Systems

- Technical Aspects of Algorithms for Explanation

- Theoretical Aspects of Explanation and Interpretability

- Ethics in AI, GenAI and Agentic AI

- Argumentation Theory for Explainable AI, GenAI and Agentic AI

- Natural Language Processing for Explainable AI, GenAI and Agentic AI

- Human-Machine Interaction for Explainable AI, GenAI and Agentic AI

- Fairness and Bias Auditing

- Privacy-Preserving Explanations

- Privacy by Design Approaches for Human Data

- Monitoring and Understanding System Behavior

- Successful Applications of Interpretable AI Systems

- Demo and Proof of Concepts with Explainable Results