Call for Papers
We invite submissions of previously unpublished papers, in two tracks.
Full paper track: In this track, we invite papers up to 6 pages with unlimited references and supplementary materials.
Demo track: In this track, we invite papers up to 4 pages that demonstrate software libraries, XAI-related frameworks, visualization tools, or applications of machine learning that involve a major XAI component. Accepted demos will present live demonstrations during the poster session.
We encourage submissions that incorporate interpretability or explainable AI, particularly those that focus on real-world applications. Topics of interest include (but are not limited to):
- Applications of XAI in Healthcare, Law, and Natural Sciences
- XAI for model auditing (E.g.: Fairness, Robustness)
- Applications of XAI for model debugging (E.g.: in NLP, CV)
- Usage of XAI tools for downstream tasks (E.g.: uncertainty estimation)
- Definitions and theory of XAI inspired by practical considerations
- Failures of XAI methods (such as mentioned in here or in here)
One of the goals of this workshop is to understand how XAI is applied in practice. To this end, we require that authors of submitted papers separately address the following survey questions to the best of their ability:
- Please provide a concise overview of your work for someone who isn’t an expert in your field. Elaborate on the role of explainability in your work
- What motivated your choice to incorporate explainability into your approach for this problem? In other words, what limitations or drawbacks are associated with using methods that lack explainability?
- Which specific method for achieving explainability do you employ in your work? For instance, do you utilize techniques like LIME, SHAP, GradCAM, influence functions or others?
We plan to share the insights derived from this survey during the workshop.
Submitted work can be of preliminary nature. We also invite position papers that provide a commentary on the current state of XAI or its usage in practice, as these may be of broader interest.
This workshop is non-archival, and will not have formal proceedings. All the accepted papers will be publicly available on our workshop website. The selection of oral presentations will be made based on the PC’s recommendations and the fit to the topics of the workshop. Concurrent submissions are allowed, but it is the authors’ responsibility to verify compliance with other venues’ policies.
Submission Instructions
Submissions should be anonymized and double-blind, and should use the official NeurIPS - XAI in Action 2023 template, and submit to the official openreview portal.
Deadlines
Submission deadline - September 22 October 2 (23:59 AoE), 2023
Author notification - October 20 October 27 (23:59 AoE), 2023
Camera ready deadline - November 22 (23:59 AoE), 2023
Contact
appliedXAI.neurips2023 [AT] gmail.com