Theodore Patkos

Foundation for Research and Technology Hellas

Papers

Total Citations

147

H-Index

About

Theodore Patkos is a leading researcher at the intersection of artificial intelligence, knowledge representation, and explainable AI (XAI). His work fundamentally advances how AI systems can reason transparently and justify their decisions. Patkos is best known for his landmark survey, "Argumentation and explainable artificial intelligence: a survey" (2021), which has garnered over 147 citations and serves as a foundational reference for the field. This work systematically demonstrates how abstract argumentation frameworks can provide step-by-step reasoning, handle uncertainty, and offer clear justifications for AI outputs—a critical capability for building trust in autonomous systems. Beyond this, Patkos has made significant contributions to formal argumentation theory, logic-based reasoning, and the development of intelligent agents that can explain their behavior. His research is particularly impactful in domains requiring high-stakes decision-making, where understanding the "why" behind an AI's conclusion is as important as the conclusion itself. Through his work, Patkos is helping to shape a future where AI is not only powerful but also accountable and understandable.