Special Track on Explainable AI–Guided Learning (XAI-GL 2026)
The rapid deployment of machine learning systems in high-stakes environments has intensified the need for transparency, accountability, and interpretability. Despite their success, most deep learning and ensemble models remain inherently difficult to interpret, leading to limited trust, regulatory challenges, and reduced usability in real-world decision-making contexts. Explainable AI (XAI) has emerged as a response to this challenge, focusing primarily on post-hoc explanation methods such as feature attribution, saliency maps, or surrogate models. However, these approaches often decouple prediction and explanation, resulting in explanations that may not faithfully reflect the true reasoning of the model.
Explainable AI–Guided Learning (XAI-GL) addresses this limitation by integrating explainability directly into the learning process. Instead of explaining a model after training, explanations become part of the learning objective itself. This paradigm opens new research directions where interpretability constraints and explanation quality influence model optimization, rather than being evaluated externally. This shift enables the development of systems that are not only interpretable but also inherently designed to be explainable, bridging the gap between human cognitive processes and machine learning representations.
This special track welcomes original contributions addressing theoretical, methodological, and applied aspects of explainable AI–guided learning. Topics include, but are not limited to:
- Explainable AI–guided learning frameworks
- Interpretable and self-explaining machine learning models
- Causal inference and causal representation learning
- Explainability-driven feature selection and dimensionality reduction
- Human-in-the-loop learning with explanation feedback
- Explainable reinforcement learning
- Counterfactual and contrastive explanations for learning improvement
- Evaluation metrics for explainability-guided systems
- Trustworthy and responsible AI systems
- Applications in healthcare, education, industry, and social good
- Multimodal explainability and explainable data fusion
All submissions for this special track must be written in English and conform to the Springer LNCS proceedings format with the following page limits: 15 pages for papers including references. Submitted papers will undergo a “double-blind” review process, coordinated by the Program Committee. To ensure anonymity of authorship, authors must ensure that authors’ names, affiliations, funding, and any other identifying information of authorship do not appear on the title page or elsewhere in the paper. Authors must provide the complete and final list of authors at the submission stage. No addition, removal, or change in the order of authors is allowed after submission.
Please use one of the following templates for the LNCS (Lecture Notes in Computer Science) format: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines
All paper submissions for this special track will be via Microsoft CMT (under “Special Track on Explainable AI–Guided Learning”).
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.
| Paper Submission | June 25, 2026 |
| Acceptance Notification | July 20, 2026 |
| Camera Ready | August 25, 2026 |
*All deadlines are 23:59 Anywhere on Earth time.
- Moncef Garouani (IRIT, Université Toulouse Capitole, France) <[email protected]>
