Print Email Facebook Twitter Evaluating XAI Title Evaluating XAI: A comparison of rule-based and example-based explanations Author van der Waa, J.S. (TU Delft Interactive Intelligence; TNO) Nieuwburg, Elisabeth (TNO; Universiteit van Amsterdam) Cremers, Anita (TNO) Neerincx, M.A. (TU Delft Interactive Intelligence; TNO) Date 2021 Abstract Current developments in Artificial Intelligence (AI) led to a resurgence of Explainable AI (XAI). New methods are being researched to obtain information from AI systems in order to generate explanations for their output. However, there is an overall lack of valid and reliable evaluations of the effects on users' experience of, and behavior in response to explanations. New XAI methods are often based on an intuitive notion what an effective explanation should be. Rule- and example-based contrastive explanations are two exemplary explanation styles. In this study we evaluate the effects of these two explanation styles on system understanding, persuasive power and task performance in the context of decision support in diabetes self-management. Furthermore, we provide three sets of recommendations based on our experience designing this evaluation to help improve future evaluations. Our results show that rule-based explanations have a small positive effect on system understanding, whereas both rule- and example-based explanations seem to persuade users in following the advice even when incorrect. Neither explanation improves task performance compared to no explanation. This can be explained by the fact that both explanation styles only provide details relevant for a single decision, not the underlying rational or causality. These results show the importance of user evaluations in assessing the current assumptions and intuitions on effective explanations. Subject Artificial Intelligence (AI)Contrastive explanationsDecision support systemsExplainable Artificial Intelligence (XAI)Machine learningUser evaluations To reference this document use: http://resolver.tudelft.nl/uuid:bff6a600-f6d9-4486-910b-36c8a847afa3 DOI https://doi.org/10.1016/j.artint.2020.103404 ISSN 0004-3702 Source Artificial Intelligence, 291 Part of collection Institutional Repository Document type journal article Rights © 2021 J.S. van der Waa, Elisabeth Nieuwburg, Anita Cremers, M.A. Neerincx Files PDF 1_s2.0_S0004370220301533_main.pdf 2.4 MB Close viewer /islandora/object/uuid:bff6a600-f6d9-4486-910b-36c8a847afa3/datastream/OBJ/view