Explainable, Trustworthy, and Responsible AI and Multi-Agent Systems

This book constitutes the refereed post-conference proceedings of the 7th International Workshop on Explainable and Transparent AI and Multi-Agent Systems, EXTRAAMAS 2025, held in Detroit, MI, USA, during May 19-20, 2025.

The 12 full papers and 1 short paper included in this book were carefully reviewed and selected from 23 submissions. They were organized in topical sections as follows: AI interpretation & social dimensions; LLMs & generative AI in XAI; agent architectures & inter-agent explainability; and human-XAI interaction, quality & ethics.

Inhalt

AI Interpretation & Social Dimensions.- Enhancing Surrogate Decision Trees for Reinforcement Learning with Feature Importance Matrices.- Exploiting Constraint Reasoning to Build Graphical Explanations for Mixed-Integer Linear Programming.- Explaining Autonomous Vehicles with Intention-aware Policy Graphs.- Social Explainable AI: What Is It and How to Make It Happen with CIU?- LLMs & Generative AI in XAI.- Evaluating Prompt Engineering Techniques for Accuracy and Confidence Elicitation in Medical LLMs.- LLM-based Evaluation Methodology of Explanation Strategies.- LLM-based Evaluation Methodology of Explanation Strategies.- Agent Architectures & Inter-Agent Explainability.- Ladder of Intentions: Unifying Agent Architectures for Explainability and Transferability.- Engineering Inter-Agent Explainability in BDI Agents.- Human-XAI Interaction, Quality & Ethics.- Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability.- Building a Decolonized AI Ethics and Governance Framework.- Balancing Ethical Persuasion and Explanation Transparency in XAI.- Designing for Effective Human-XAI Inter-action.