Print Email Facebook Twitter It Is Like Finding a Polar Bear in the Savannah! Concept-level AI Explanations with Analogical Inference from Commonsense Knowledge Title It Is Like Finding a Polar Bear in the Savannah! Concept-level AI Explanations with Analogical Inference from Commonsense Knowledge Author He, G. (TU Delft Web Information Systems) Balayn, A.M.A. (TU Delft Web Information Systems) Buijsman, S.N.R. (TU Delft Ethics & Philosophy of Technology) Yang, J. (TU Delft Web Information Systems) Gadiraju, Ujwal (TU Delft Web Information Systems) Contributor Hsu, Jane (editor) Yin, Ming (editor) Date 2022 Abstract With recent advances in explainable artificial intelligence (XAI), researchers have started to pay attention to concept-level explanations, which explain model predictions with a high level of abstraction. However, such explanations may be difficult to digest for laypeople due to the potential knowledge gap and the concomitant cognitive load. Inspired by recent work, we argue that analogy-based explanations composed of commonsense knowledge may be a potential solution to tackle this issue. In this paper, we propose analogical inference as a bridge to help end-users leverage their commonsense knowledge to better understand the concept-level explanations. Specifically, we design an effective analogy-based explanation generation method and collect 600 analogy-based explanations from 100 crowd workers. Furthermore, we propose a set of structured dimensions for the qualitative assessment of analogy-based explanations and conduct an empirical evaluation of the generated analogies with experts. Our findings reveal significant positive correlations between the qualitative dimensions of analogies and the perceived helpfulness of analogy-based explanations. These insights can inform the design of future methods for the generation of effective analogy-based explanations. We also find that the understanding of commonsense explanations varies with the experience of the recipient user, which points out the need for further work on personalization when leveraging commonsense explanations. Subject Human-centered Explainable AIAnalogyConcept-level ExplanationCommonsense Knowledge To reference this document use: http://resolver.tudelft.nl/uuid:13e44c38-74a8-491f-87da-7747f2d4208c DOI https://doi.org/10.1609/hcomp.v10i1.21990 Embargo date 2023-11-06 ISBN 978-1-57735-878-7 Source Proceedings of the Tenth AAAI Conference on Human Computation and Crowdsourcing Event HCOMP 2022: 10th AAAI Conference on Human Computation and Crowdsourcing, 2022-11-06 → 2022-11-10 Series Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 2769-1330, 10 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. Part of collection Institutional Repository Document type conference paper Rights © 2022 G. He, A.M.A. Balayn, S.N.R. Buijsman, J. Yang, Ujwal Gadiraju Files PDF 21990_Article_Text_26043_ ... 221013.pdf 1.16 MB Close viewer /islandora/object/uuid:13e44c38-74a8-491f-87da-7747f2d4208c/datastream/OBJ/view