# Quod erat demonstrandum? - Towards a typology of the concept of explanation for the design of explainable AI - Type: News - Source: ScienceDirect - Date: 2022-09-27 - Original: https://www.sciencedirect.com/science/article/pii/S0957417422019066?via=ihub#entry-812 - Canonical: https://overview.legal/posts/6270 - Topics: Artificial Intelligence, AI Standards, Right to Explanation, IP Address, Scientific Research, Human Resources, Cookies ## Summary > * We propose a framework for defining different types of explanations of AI systems. > * We contextualize current XAI discourses within the proposed framework. > * We highlight two broad perspectives for defining quality criteria for explainability. > * We discuss the relevance of our framework in light of current and upcoming AI regulation. ## Full text [Skip to main content](#screen-reader-main-content) [Skip to article](#screen-reader-main-title) [![Elsevier logo](https://sdfestaticassets-us-east-1.sciencedirectassets.com/shared-assets/24/images/elsevier-non-solus-new-grey.svg)ScienceDirect](/) * [Journals & Books](/browse/journals-and-books) * Help * [Search](/search) [Corporate sign in](/user/institution/login?targetURL=%2Fscience%2Farticle%2Fpii%2FS0957417422019066)[Sign in / register](/user/login?targetURL=%2Fscience%2Farticle%2Fpii%2FS0957417422019066&from=globalheader) * PDFView **PDF** Search [![Elsevier](https://sdfestaticassets-eu-west-1.sciencedirectassets.com/prod/c2f55a8e2e9eec551c546d4835e8a8bb5939b6be/image/elsevier-non-solus.png)](/journal/expert-systems-with-applications "Go to Expert Systems with Applications on ScienceDirect") ## [Expert Systems with Applications](/journal/expert-systems-with-applications "Go to Expert Systems with Applications on ScienceDirect") Available online 24 September 2022, 118888 [In Press, Journal Pre-proof](/journal/expert-systems-with-applications/articles-in-press)[HelpWhat are Journal Pre-proof articles?](https://service.elsevier.com/app/answers/detail/a%5Fid/22799/supporthub/sciencedirect/ "What are Journal Pre-proof articles?") [![Expert Systems with Applications](https://ars.els-cdn.com/content/image/S09574174.gif)](/journal/expert-systems-with-applications) # Quod erat demonstrandum? - Towards a typology of the concept of explanation for the design of explainable AI Author links open overlay panel[FedericoCabitzaabEnvelope](#!)[AndreaCampagneraEnvelope](#!)[GianclaudioMalgieridEnvelope](#!)[ChiaraNatalicEnvelope](#!)[DavidSchneebergereEnvelope](#!)[KarlStoegereEnvelope](#!)[AndreasHolzingerfPersonEnvelope](#!) Show moreNavigate Down ShareShare Cited ByCite [Get rights and content](https://s100.copyright.com/AppDispatchServlet?publisherName=ELS&contentID=S0957417422019066&orderBeanReset=true) Under a Creative Commons [license](https://creativecommons.org/licenses/by/4.0/) Open access ## Highlights • We propose a framework for defining different types of explanations of AI systems. • We contextualize current XAI discourses within the proposed framework. • We highlight two broad perspectives for defining quality criteria for explainability. • We discuss the relevance of our framework in light of current and upcoming AI regulation. • We confer fundamental aspects for future research of XAI scholars. ## Abstract In this paper, we present a fundamental framework for defining different types of explanations of AI systems and the criteria for evaluating their quality. Starting from a structural view of how explanations can be constructed, i.e., in terms of an explanandum (what needs to be explained), multiple explanantia (explanations, clues, or parts of information that explain), and a relationship linking explanandum and explanantia, we propose an explanandum-based typology and point to other possible typologies based on how explanantia are presented and how they relate to explanandia. We also highlight two broad and complementary perspectives for defining possible quality criteria for assessing explainability: epistemological and psychological (cognitive). These definition attempts aim to support the three main functions that we believe should attract the interest and further research of XAI scholars: clear inventories, clear verification criteria, and clear validation methods. ## Keywords Explainable AI XAI Explanations Taxonomy Artificial intelligence Machine learning Recommended articles ## Data availability No data was used for the research described in the article. ## Cited by (0) © 2022 The Author(s). Published by Elsevier Ltd. ## Recommended articles Navigate Down No articles found. ## Article Metrics Navigate Down [View article metrics](https://plu.mx/plum/a/?doi=10.1016/j.eswa.2022.118888) [![Elsevier logo with wordmark](https://sdfestaticassets-us-east-1.sciencedirectassets.com/shared-assets/47/images/elsevier-non-solus-new-with-wordmark.svg)](https://www.elsevier.com/) * [About ScienceDirect](https://www.elsevier.com/solutions/sciencedirect) * [Remote access](/user/institution/login?targetURL=) * [Shopping cart](https://sd-cart.elsevier.com/?) * [Advertise](http://elsmediakits.com) * [Contact and support](https://service.elsevier.com/app/contact/supporthub/sciencedirect/) * [Terms and conditions](https://www.elsevier.com/legal/elsevier-website-terms-and-conditions) * [Privacy policy](https://www.elsevier.com/legal/privacy-policy) We use cookies to help provide and enhance our service and tailor content and ads. By continuing you agree to the [**use of cookies**](https://www.sciencedirect.com/legal/use-of-cookies). Copyright © 2022 Elsevier B.V. or its licensors or contributors. ScienceDirect® is a registered trademark of Elsevier B.V. ScienceDirect® is a registered trademark of Elsevier B.V. [![RELX group home page](https://sdfestaticassets-us-east-1.sciencedirectassets.com/shared-assets/60/images/logo-relx-tm.svg)](https://www.relx.com/) --- Generated by overview.legal · https://overview.legal/posts/6270 · 2026-08-22