Keynote speech
Evaluating Explainable AI:
Are We Asking the Wrong Questions?
Explainable AI (XAI) has made remarkable progress in developing methods to generate explanations for increasingly complex models. Yet despite this technical success, there is little consensus on how to evaluate these explanations or what makes an explanation ‘good’. This keynote argues that the field has been asking the wrong questions.
I will challenge several common assumptions about explanation evaluation, including the primacy of explanation fidelity and the idea that improving predictive performance inevitably comes at the expense of human understanding. Drawing on examples from my own research and the broader XAI literature, I will show how explanation needs vary across users, tasks, and contexts, and why no single notion of explainability can satisfy the diverse needs of different stakeholders.
I conclude by arguing for a shift in how XAI is evaluated. Rather than continuing to evaluate explanations using isolated case studies and inconsistent metrics, XAI research should move toward more standardized evaluation protocols that enable meaningful comparisons. Only then can XAI move from producing explanations to producing explanations that genuinely support human understanding and decision-making.
Biography
Prof. Nava Tintarev is a Full Professor in Explainable AI at Maastricht University in the Department of Advanced Computing Sciences (DACS). Her interdisciplinary work bridges computer science and human-centered evaluation, focusing on making AI systems more transparent and increasing user control.
Prof. Tintarev specializes in developing interactive explanation interfaces for recommender systems and search technologies, emphasizing user empowerment and decision support. She is a lab director of the ICAI TAIM lab, working on trustworthy AI in media.
She was a founding principal investigator of ROBUST, a €87 million Dutch national initiative advancing trustworthy AI. Her research has also been supported by major organizations including IBM, Twitter, and the European Commission.
Recognized as a Senior Member of the ACM in 2020, Prof. Tintarev’s team has received multiple best paper awards for research contributions at CHI, CHIIR, Hypertext, UMAP, and HCOMP. Her work underscores the importance of transparency and user agency, aiming to support better decision-making with AI.
She is active in Dutch research policy as the Chair of the round table member for informatics, and as a board member the ICT-Research Platform Netherlands (IPN).