SLAVE TO THE ALGORITHM ? WHY A ‘ RIGHT TO AN EXPLANATION ’ IS PROBABLY NOT THE REMEDY YOU ARE LOOKING FOR

By M. I. V. Eale. 2017

Subfields: Safety, Robustness & Interpretability, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

In AI Ethics, Fairness & Society

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Informativeness [5, 44, 21, 25, 26, 45, 30, 32, 34, 35, 37, 38, 41, 46, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 63, 64, 65, 66, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 86, 87, 88, 89, 59, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 1”
Fairwashing: the risk of rationalization (2019, background): “…right to explanation as deﬁned in current regulations [15] does not give precise directives on what it means to provide a “valid explanation” [33, 13], there is a legal loophole that can be used by dishonest companies to cover up the possible unfairness of their black-box models by providing…”
The growing ubiquity of algorithms in society: implications, impacts and innovations (2018, unknown): “explanation for more opaque systems [74,76].”
Enslaving the Algorithm: From a “Right to an Explanation” to a “Right to Better Decisions”? (2018, background): “The former article 12 has also been revamped to a new article 15 and now includes a right to access to “meaningful information about the logic involved, as well as the significance and the envisaged consequences of such processing” (article 15(1)(h)).”
The ethics of algorithms: key problems and solutions (2020, unknown): “However, explanations for ML algorithms are constrained by the type of explanation sought, the fact that decisions are often multi-dimensional in their nature, and that different users may require different explanations (Edwards and Veale 2017).”
The hidden assumptions behind counterfactual explanations and principal reasons (2019, background): “sions, and, if it exists, whether and when it requires an explanation of specific decisions or the model [4, 5, 10, 19, 26, 28, 39, 46].”
Four Responsibility Gaps with Artificial Intelligence: Why they Matter and How to Address them (2021, background): “Also, it has been doubted that the GDPR provisions guarantee sufficient transparency and accessibility to these mechanisms for those who are subject to them (Edwards & Veale, 2017; Wachter et al., 2017).”
Ethical governance is essential to building trust in robotics and artificial intelligence systems (2018, background): “There is a growing literature on transparency; see, for instance, work on transparency and explainability in robot systems [27,41,42], transparency in relation to the EU General Data Protection Regulation (GDPR) [43,44] and on the limitations of transparency [45].”
Human-AI Interactions in Public Sector Decision-Making:"Automation Bias"and"Selective Adherence"to Algorithmic Advice (2021, background): “…been increasingly voiced by scholars in the context of a growing reliance on AI tools in the public sector and high-stakes scenarios (Cobbe 2019; Edwards and Veale 2017; Medium—Open Letter Concerned AI Researchers 2019; Zerilli et al. 2019), and increasingly so also by public administration…”
Algorithms that remember: model inversion attacks and data protection law (2018, background): “In cases where outliers might be vulnerable as well as powerful this is problematic: we might suspect it is they who need data protection the most [4].”
Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making (2018, background): “Yet issues like fairness have been shown to come with technically difficult to reconcile, or even irreconcilable trade-offs—something well-demonstrated by Alexandra Chouldechova’s impossibility theorem illustrating that independently plausible formal definitions of fairness can be statistically inco”