Post-hoc vs ante-hoc explanations: xAI design guidelines for data scientists

• Published in: Cognitive systems research Vol. 86; p. 101243
• Main Authors: Retzlaff, Carl O., Angerschmid, Alessa, Saranti, Anna, Schneeberger, David, Röttger, Richard, Müller, Heimo, Holzinger, Andreas
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2024
• Subjects: Ante-hoc; Explainable AI; Explanations; Guideline; Post-hoc; xAI; Post-hoc; xAI; Guideline; Explainable AI; Ante-hoc; Explanations
• ISSN: 1389-0417; 1389-0417
• DOI: 10.1016/j.cogsys.2024.101243

The growing field of explainable Artificial Intelligence (xAI) has given rise to a multitude of techniques and methodologies, yet this expansion has created a growing gap between existing xAI approaches and their practical application. This poses a considerable obstacle for data scientists striving to identify the optimal xAI technique for their needs. To address this problem, our study presents a customized decision support framework to aid data scientists in choosing a suitable xAI approach for their use-case. Drawing from a literature survey and insights from interviews with five experienced data scientists, we introduce a decision tree based on the trade-offs inherent in various xAI approaches, guiding the selection between six commonly used xAI tools. Our work critically examines six prevalent ante-hoc and post-hoc xAI methods, assessing their applicability in real-world contexts through expert interviews. The aim is to equip data scientists and policymakers with the capacity to select xAI methods that not only demystify the decision-making process, but also enrich user understanding and interpretation, ultimately advancing the application of xAI in practical settings. •xAI has become a large and complicated field.•There is a gap between theory and practice.•There are many diverse xAI techniques.•The xAI field is going to be incomprehensible for the non-expert.•Short, clear, crisp, concise guidelines for data scientists are needed.