What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research

Langer, Markus; Oster, Daniel; Speith, Timo; Hermanns, Holger; Kästner, Lena; Schmidt, Eva; Sesing, Andreas; Baum, Kevin

doi:10.1016/j.artint.2021.103473

Cited by 295 publications

(240 citation statements)

References 166 publications

Supporting

Mentioning

191

Contrasting

Order By: Relevance

“…However, the traits that render an explanation satisfying are not independent of the audience’s characteristics and expectations. To this end, a series of recent papers address this exact question ( van den Berg and Kuiper, 2020 ; Langer et al, 2021 ), highlighting the need to consider the point of view of the various stakeholders. As a consequence, explanations should be tailored to the specific audience they are intended for, aiming at conveying the necessary information in a clear way.…”

Section: Future Directionsmentioning

confidence: 99%

Principles and Practice of Explainable Machine Learning

2021

View full text Add to dashboard Cite

Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However, such a highly positive impact is coupled with a significant challenge: how do we understand the decisions suggested by these systems in order that we can trust them? In this report, we focus specifically on data-driven methods—machine learning (ML) and pattern recognition models in particular—so as to survey and distill the results and observations from the literature. The purpose of this report can be especially appreciated by noting that ML models are increasingly deployed in a wide range of businesses. However, with the increasing prevalence and complexity of methods, business stakeholders in the very least have a growing number of concerns about the drawbacks of models, data-specific biases, and so on. Analogously, data science practitioners are often not aware about approaches emerging from the academic literature or may struggle to appreciate the differences between different methods, so end up using industry standards such as SHAP. Here, we have undertaken a survey to help industry practitioners (but also data scientists more broadly) understand the field of explainable machine learning better and apply the right tools. Our latter sections build a narrative around a putative data scientist, and discuss how she might go about explaining her models by asking the right questions. From an organization viewpoint, after motivating the area broadly, we discuss the main developments, including the principles that allow us to study transparent models vs. opaque models, as well as model-specific or model-agnostic post-hoc explainability approaches. We also briefly reflect on deep learning models, and conclude with a discussion about future research directions.

show abstract

Section: Future Directionsmentioning

confidence: 99%

Principles and Practice of Explainable Machine Learning

2021

View full text Add to dashboard Cite

show abstract

“…Investigating these trade-offs of stakeholders' interests provides a fruitful direction for future research (Langer et al, 2021).…”

Section: Limitations and Main Implicationsmentioning

confidence: 99%

Spare me the details: How the type of information about automated interviews influences applicant reactions

Langer

Baum

König

et al. 2021

Int J Selection Assessment

Self Cite

View full text Add to dashboard Cite

show abstract

“…Where the ML-based systems are used by human experts to inform decision-making, a local and contemporaneous explanation will be required in order to decide whether to act on a specific prediction in real time. Consent and Control . XAI methods may also play a role in enabling stakeholders to better exercise their own human autonomy in relation to an ML-model [24]. Appropriate explanations could enable users to give their informed consent to recommendations by ML-based personal assistants, for example, or, in the case of an AV, to understand a transition demand sufficiently to resume effective hands-on control of the system.…”

Section: Stakeholders and Explanationsmentioning

confidence: 99%

Artificial intelligence explainability: the technical and ethical dimensions

McDermid

Jia

Porter

et al. 2021

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

In recent years, several new technical methods have been developed to make AI-models more transparent and interpretable. These techniques are often referred to collectively as ‘AI explainability’ or ‘XAI’ methods. This paper presents an overview of XAI methods, and links them to stakeholder purposes for seeking an explanation. Because the underlying stakeholder purposes are broadly ethical in nature, we see this analysis as a contribution towards bringing together the technical and ethical dimensions of XAI. We emphasize that use of XAI methods must be linked to explanations of human decisions made during the development life cycle. Situated within that wider accountability framework, our analysis may offer a helpful starting point for designers, safety engineers, service providers and regulators who need to make practical judgements about which XAI methods to employ or to require. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.

show abstract

What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research

Cited by 295 publications

References 166 publications

Principles and Practice of Explainable Machine Learning

Principles and Practice of Explainable Machine Learning

Spare me the details: How the type of information about automated interviews influences applicant reactions

Artificial intelligence explainability: the technical and ethical dimensions

Contact Info

Product

Resources

About