CHIME: Causal Human-in-the-Loop Model Explanations

Conference Paper (2022)
Author(s)

S. Biswas (TU Delft - Web Information Systems)

L. Corti (TU Delft - Web Information Systems)

Stefan Buijsman (TU Delft - Ethics & Philosophy of Technology)

Jie Yang (TU Delft - Web Information Systems)

Research Group
Web Information Systems
Copyright
© 2022 S. Biswas, L. Corti, S.N.R. Buijsman, J. Yang
DOI related publication
https://doi.org/10.1609/hcomp.v10i1.21985
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 S. Biswas, L. Corti, S.N.R. Buijsman, J. Yang
Research Group
Web Information Systems
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. @en
Pages (from-to)
27-39
ISBN (print)
978-1-57735-878-7
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Explaining the behaviour of Artificial Intelligence models has become a necessity. Their opaqueness and fragility are not tolerable in high-stakes domains especially. Although considerable progress is being made in the field of Explainable Artificial Intelligence, scholars have demonstrated limits and flaws of existing approaches: explanations requiring further interpretation, non-standardised explanatory format, and overall fragility. In light of this fragmentation, we turn to the field of philosophy of science to understand what constitutes a good explanation, that is, a generalisation that covers both the actual outcome and, possibly multiple, counterfactual outcomes. Inspired by this, we propose CHIME: a human-in-the-loop, post-hoc approach focused on creating such explanations by establishing the causal features in the input. We first elicit people's cognitive abilities to understand what parts of the input the model might be attending to. Then, through Causal Discovery we uncover the underlying causal graph relating the different concepts. Finally, with such a structure, we compute the causal effects different concepts have towards a model's outcome. We evaluate the Fidelity, Coherence, and Accuracy of the explanations obtained with CHIME with respect to two state-of-the-art Computer Vision models trained on real-world image data sets. We found evidence that the explanations reflect the causal concepts tied to a model's prediction, both in terms of causal strength and accuracy.

Files

21985_Article_Text_26038_1_2_2... (pdf)
(pdf | 15.4 Mb)
- Embargo expired in 06-11-2023
License info not available