Put it to the Test: Getting Serious About Explanation in Explainable Artificial Intelligence
Open Access
- 6 June 2025
- journal article
- research article
- Published by Springer Nature in Minds and Machines
- Vol. 35 (2) , 1-28
Abstract
Artificial intelligence (AI) has become a topic of major interest to philosophers of science. Among the issues commonly discussed is AI’s opacity. To remedy opacity, scientists have provided methods commonly subsumed under the label ‘eXplaibable Artificial Intelligence’ (XAI) that aim to make AI and its outputs ‘interpretable’ and ‘explainable’. However, there is little interaction between developments in XAI and philosophical debates on scientific explanation. We here improve on this situation and argue for a descriptive and a normative thesis: (i) When suitably embedded into scientific research processes, XAI methods’ outputs can facilitate genuine scientific understanding. (ii) In order for XAI outputs to fulfill this function, they should be made testable. We will support our theses by building on recent and long-standing ideas from philosophy of science, by comparing them to a recent framework from the XAI community, and by showcasing their applicability to case studies from the life sciences.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (508844757)
- Ministerium für Kultur und Wissenschaft des Landes Nordrhein-Westfalen (111.08.03.05-133974)
- Bundesministerium für Forschung, Technologie und Raumfahrt (031L0264)
- Technische Universität Dortmund
This publication has 88 references indexed in Scilit:
- Explainable AI and Causal Understanding: Counterfactual Approaches ConsideredMinds and Machines, 2023
- The Importance of Understanding Deep LearningErkenntnis, 2022
- Defining Explanation and Explanatory Depth in XAIMinds and Machines, 2022
- Two Dimensions of Opacity and the Deep Learning PredicamentMinds and Machines, 2021
- The explanation game: a formal framework for interpretable machine learningSynthese, 2020
- Model Explanation Versus Model-Induced ExplanationFoundations of Science, 2020
- The Pragmatic Turn in Explainable Artificial Intelligence (XAI)Minds and Machines, 2019
- Towards a realistic success-to-truth inference for scientific realismSynthese, 2016
- When mechanistic models explainSynthese, 2006
- Scientific Discovery and Theory-Confirmation1985