W3: On the importance of explanation content for explainable AI: Towards an explanation content research agenda

Aim of the Workshop

The workshop aims to advance the study of explanation content in XAI through three interconnected aims: theoretical, methodological, and practical.

First, the workshop seeks to establish a shared understanding of explanation content and its role within the broader landscape of XAI and HCI research. To this end, participants will critically compare theoretical approaches and conceptual frameworks from HCI, cognitive science, linguistics, human-centered AI, and related areas with the aim of developing a common ontological foundation for explanation content research.

Second, the workshop will investigate the methodological challenges of eliciting, designing, and evaluating explanation content in a human-centered way. This includes discussing methods for identifying user information needs, eliciting explanation content and mapping it to user questions and tasks, designing explanation content, and evaluating whether explanations effectively support users’ understanding and decision making.

Third, the workshop will explore the practical implementation of explanation content in real-world AI systems. While many XAI methods focus on generating explanations from model-intrinsic properties, integrating appropriate explanation content into deployed AI systems raises additional challenges related to system design, user interfaces, domain constraints, and organizational contexts.

By addressing these three aims, the workshop seeks to elevate explanation content from a largely unexamined research concern to a better defined, grounded foundation for both research and practice in human-centered AI systems. In doing so, the workshop aims to shift the current XAI research from a feasibility-driven focus on explanation types (e.g., causal, counterfactual, example-based explanations) towards a theoretically grounded, user needs-driven focus on explanation content as the basis for effective explanations.

Workshop topics

Topics include, but are not limited to:

• Theoretical foundations and conceptual frameworks for explanation content in XAI
• Ontological foundations for explanation content
• Relationships between explanation types, explanation formats, and explanation content
• Methods for eliciting explanation content from users and stakeholders, and categorizing it according to their roles, expertise levels, tasks, and decision contexts
• Methods for evaluating the effectiveness of explanation content in supporting user understanding, decision making, and appropriate reliance
• Design and visualization of explanation content for different stakeholders, including end-users, developers, auditors, and regulators
• Explanation content requirements in regulatory and compliance contexts, including implications of frameworks such as the EU AI Act
• Explanation content for generative AI and large language models
• Domain-specific challenges in explanation content design (e.g., healthcare, finance, education, industry)
• Practical approaches for integrating explanation content into deployed AI systems
• Case studies of explanation content elicitation, design, and integration in AI systems

Guidelines to prospective authors

Submission for the Workshop

Interested participants should submit a position paper (around 1000 words without references) on the importance of explanation content for explainable AI.

Prospective authors should submit their proposals in PDF format through the HCII Conference Management System (CMS).

Submission for the Conference Proceedings

The contributions to be presented in the context of Workshops will not be automatically included in the Conference proceedings.

However, after consultation with the Workshop organizer(s), authors of accepted Workshop proposals who are registered for the Conference are welcome to submit, through the Conference Management System (CMS), an extended version of their Workshop contribution to be considered, following further peer review, for presentation at the Conference and inclusion in the “Late Breaking” volumes of the Conference proceedings, either in the LNCS as a long paper (typically 12 pages, but no less than 10 and no more than 20 pages), or in the CCIS as a short paper/extended poster abstract (typically 6 pages, but no less than 4 and no more than 11).

Workshop organizers are also encouraged to consider and explore the (additional) possibility of preparing a paper (short or long) which will present the collaborative efforts of their Workshop participants, and can be submitted in October 2026 to be considered for publication in the context of the HCII 2027 Conference Proceedings.

Workshop organizers

Helmut Degen
Dr. Helmut Degen is Senior Key Expert for User Experience at Siemens Corporation, Princeton, NJ, USA. Helmut conducts explainable AI (XAI) research for industrial applications at Siemens with a focus on human-computer interaction. Helmut is also the co-chair of the yearly, international conference on Artificial Intelligence in Human-Computer Interaction (AI-HCI) affiliated with the HCI International Conference. He has received a Masters of Science (in German “Diplom-Informatiker”) from the Karlsruhe Institute of Technology and a PhD in Information Science from the Freie Universität Berlin (both in Germany).

George Margetis
Dr. George Margetis is a computer scientist specializing in Human-Computer Interaction (HCI), Human-Centered Artificial Intelligence (HCAI), Ambient Intelligence (AmI), Extended Reality (XR), and Digital Accessibility. Since 2021, he leads the Human-Centered AI research and development activities of the HCI Laboratory of FORTH-ICS, Greece. In this role, he has advocated for human-centric and inclusive design of AI systems, ensuring outcomes that are technologically robust, transparent, usable, and aligned with human values. He is also the co-chair of the yearly, international conference on Human-Centered Design, Operation and Evaluation of Mobile Communications (MOBILE), affiliated with the HCI International Conference.

Stavroula Ntoa
Dr. Stavroula Ntoa is a Computer Scientist specializing in Design for All, software accessibility, usability engineering, and User Experience (UX) research and design. She is a Principal Researcher at the HCI Laboratory of FORTH-ICS, Greece, leading the accessible UX research and design activities of the lab. Her research interests focus on Design for All and Universal Access of modern interactive technologies, adaptive and intelligent interfaces, as well as inclusiveness and user experience research in intelligent and Artificial Intelligence environments. She serves as co-chair of the annual International Conference on Artificial Intelligence in Human-Computer Interaction, affiliated with the HCI International Conference.