Show simple item record

dc.contributor.authorNyrup, Rune
dc.contributor.authorRobinson, Diana
dc.date.accessioned2022-04-07T01:02:36Z
dc.date.available2022-04-07T01:02:36Z
dc.date.issued2022
dc.identifier.issn1388-1957
dc.identifier.other35250370
dc.identifier.otherPMC8885497
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/335853
dc.descriptionFunder: microsoft research
dc.description.abstractExplainable artificial intelligence (XAI) is an emerging, multidisciplinary field of research that seeks to develop methods and tools for making AI systems more explainable or interpretable. XAI researchers increasingly recognise explainability as a context-, audience- and purpose-sensitive phenomenon, rather than a single well-defined property that can be directly measured and optimised. However, since there is currently no overarching definition of explainability, this poses a risk of miscommunication between the many different researchers within this multidisciplinary space. This is the problem we seek to address in this paper. We outline a framework, called Explanatory Pragmatism, which we argue has two attractive features. First, it allows us to conceptualise explainability in explicitly context-, audience- and purpose-relative terms, while retaining a unified underlying definition of explainability. Second, it makes visible any normative disagreements that may underpin conflicting claims about explainability regarding the purposes for which explanations are sought. Third, it allows us to distinguish several dimensions of AI explainability. We illustrate this framework by applying it to a case study involving a machine learning model for predicting whether patients suffering disorders of consciousness were likely to recover consciousness.
dc.description.sponsorshipLeverhulme Trust (through Leverhulme Centre for the Future of Intelligence)
dc.languageeng
dc.publisherSpringer
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourcenlmid: 101248311
dc.subjectUnderstanding
dc.subjectExplanation
dc.subjectExplainable Artificial Intelligence
dc.subjectMedical Artificial Intelligence
dc.subjectXai
dc.subjectEthics Of Artificial Intelligence
dc.titleExplanatory pragmatism: a context-sensitive framework for explainable medical AI.
dc.typeArticle
dc.date.updated2022-04-07T01:02:35Z
prism.issueIdentifier1
prism.publicationNameEthics Inf Technol
prism.volume24
dc.identifier.doi10.17863/CAM.83286
dcterms.dateAccepted2022-01-05
rioxxterms.versionofrecord10.1007/s10676-022-09632-3
rioxxterms.versionVoR
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0/
dc.contributor.orcidNyrup, Rune [0000-0002-9880-6912]
dc.contributor.orcidRobinson, Diana [0000-0001-7468-0123]
dc.identifier.eissn1572-8439
pubs.funder-project-idWellcome Trust (213660/Z/18/Z)
pubs.funder-project-idLeverhulme Trust (RC-2015-067)
pubs.funder-project-idLeverhulme Trust (RC-2015-067)
cam.issuedOnline2022-02-28


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International