The 2nd Human-Centric eXplainable AI in Education (HEXED) Workshop will be held in conjunction with EDM (Educational Data Mining) 2025. The workshop aims to bring together a specialized community of researchers who can work together to (1) establish a shared vision and common vocabulary for XAI in education, (2) facilitate the exchange of recent research and best practices, (3) brainstorm practical methods to enhance model transparency that are specific to the education domain, and (4) define evaluation metrics for assessing explanations and interpretability with teachers, students, and parents. We plan to achieve this through lively debate and discussion surrounding the current and future needs of the community.
The workshop will be held on 20 July 2025 in Palermo, Italy. This is a full-day hybrid workshop and will feature a mix of poster presentations, a lively panel discussion, and interactive sessions to facilitate collaboration.
Themes
- The need for greater explainability in education.
- The case for intrinsic vs. post-hoc explainability.
- Ensuring explanation faithfulness.
- Designing evaluation metrics and methods for assessing explanations and/or models.
- Aligning explanations with teachers’ and students’ needs.
- Generating actionable explanations as a basis for classroom interventions and personalized learning.
- The role of LLMs in Explainable AI.
Proceedings
To be announced.
Schedule
The workshop will be held from 9:00am to 5:00pm. Click here for the schedule and accepted papers.
Registration
The registration is managed by the EDM 2025 main conference organization at https://educationaldatamining.org/edm2025/.
Organizers
The workshop organizers are listed below. Click here to learn more about them or to see the full program committee.
- Vinitra Swamy, EPFL
- Jakub Kuzilek, Humboldt-Universität zu Berlin
- Juan D. Pinto, University of Illinois Urbana‐Champaign
- Luc Paquette, University of Illinois Urbana-Champaign
- Tanja Käser, EPFL
- Qianhui (Sophie) Liu, University of Illinois Urbana-Champaign
- Lea Cohausz, University of Mannheim