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.
Original language | English |
---|---|
Title of host publication | Proceedings of the Tenth AAAI Conference on Human Computation and Crowdsourcing |
Editors | Jane Hsu, Ming Yin |
Pages | 27-39 |
Number of pages | 13 |
DOIs | |
Publication status | Published - 2022 |
Event | HCOMP 2022: 10th AAAI Conference on Human Computation and Crowdsourcing - Duration: 6 Nov 2022 → 10 Nov 2022 |
Publication series
Name | Proceedings of the AAAI Conference on Human Computation and Crowdsourcing |
---|---|
ISSN (Print) | 2769-1349 |
Conference
Conference | HCOMP 2022: 10th AAAI Conference on Human Computation and Crowdsourcing |
---|---|
Period | 6/11/22 → 10/11/22 |
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-careOtherwise 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.
Keywords
- Explainable AI
- Human-In-the-Loop
- Causal Inference