Stakeholders in Explainable AI

By Alun David Preece, Daniel Harborne, Dave Braines, Richard J. Tomsett, Supriyo Chakraborty. 2018

183 citations recorded by the source corpus.

There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general consensus over what is meant by ‘explainable’ and ‘interpretable’. In this paper, we argue that this lack of consensus is due to there being several distinct stakeholder communities. We note that, while the concerns of the individual communities are broadly compatible, they are not identical, which gives rise to different intents and requirements for explainability/ interpretability. We use the software engineering distinction between validation and verification, and the epistemological distinctions between knowns/unknowns, to tease apart the concerns of the stakeholder communities and highlight the areas where their foci overlap or diverge. It is not the purpose of the authors of this paper to ‘take sides’ — we count ourselves as members, to varying degrees, of multiple communities — but rather to help disambiguate what stakeholders mean when they ask ‘Why?’ of an AI.

Subfields: Artificial Intelligence, Safety Research

How researchers see this paper

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

In Artificial Intelligence

In Safety Research

Citations in the corpus

Rapid Trust Calibration through Interpretable and Uncertainty-Aware AI (2020, background): “Although important studies from the HCI community have probed these questions,(67,86,87) more collaborative work between AI and HCI researchers, as well as statisticians and others experienced in communicating about uncertainty, will be crucial for focusing technical research toward developing metho”
Explainable machine learning in deployment (2019, background): “[49] describe how stakeholders have different needs for explainability.”
Explainable AI for Intelligence Augmentation in Multi-Domain Operations (2019, methodology): “Based on this framework, we proposed a ‘layered’ approach to offer different explanations tailored to the different stakeholders (Preece et al. 2018) by means of a composite explanation object that packs together all the information needed to satisfy multiple stakeholders, and can be unpacked…”
Human-Centered Explainable AI (XAI): From Algorithms to User Experiences (2021, background): “Many have summarized common user groups that demand explainability and what they would use AI explanations for [11, 49, 83]:”
Explainability fact sheets: a framework for systematic assessment of explainable approaches (2019, background): “Other researchers [41, 52] highlighted the importance of considering the stakeholders of an explanation before validating it – intended application (O7) and audience (O6).”
Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges (2020, background): “Research-wise, the ﬁeld is maturing in terms of methods surveys [75,41,120,96,1,6,23,15], further consolidation of terms and knowledge [42,22,82,97,88,17], and work about deﬁning interpretability or evaluation of IML methods [74,73,95,49].”