The Limits of Value Transparency in Machine Learning

Bibliographic Data

ID10705472
AuthorsRune Nyrup (0000-0002-9880-6912, University of Cambridge, corresponding author)
Year2022
Volume89
Issue5
Pages1054-1064
Publication date2022-12-01
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenuePhilosophy of Science (JOURNAL)
Journal identifiersISSN: 0031-8248 • E-ISSN: 1539-767X
PublisherCambridge University Press (CUP) (PUBLISHER)
DOI10.1017/psa.2022.61
OpenAlexW4282829248
LanguageEN
Citations received4
References cited10

Transparency has been proposed as a way of handling value-ladenness in machine learning (ML). This article highlights limits to this strategy. I distinguish three kinds of transparency: epistemic transparency, retrospective value transparency, and prospective value transparency. This corresponds to different approaches to transparency in ML, including so-called explainable artificial intelligence and governance based on disclosing information about the design process. I discuss three sources of value-ladenness in ML—problem formulation, inductive risk, and specification gaming—and argue that retrospective value transparency is only well-suited for dealing with the first, while the third raises serious challenges even for prospective value transparency

Computer security · Corporate governance · Economics · Machine learning · Management · Transparency (behavior) · Value (mathematics) · Artificial Intelligence · Computer Science · Ethics and Social Impacts of AI · Explainable Artificial Intelligence (XAI · Qualitative Comparative Analysis Research

Tools

Open DOIOpen Access