Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue

Chazette, Larissa; Brunotte, Wasja; Speith, Timo

doi:10.1109/re51729.2021.00025

Cited by 59 publications

(63 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It needs to be clarified which explanations, under which conditions, can justify a stakeholder's belief that the system works properly. With this in mind, we suggest paying particular attention to the context in which an explanation is given, as different stakeholders and situations might require different explanations to make the system trustworthy [5], [6].…”

Section: Future Research Directionsmentioning

confidence: 99%

“…Many see explainability as a suitable means to foster stakeholder trust [5], [6]: If we better understand how the system produces its outputs and the explanation for a given output fits with our expectations of how a good decision should be made, this explanation presents a reason to trust the system. Thus, at first glance, a requirement for explainability seems to be more suitable than to have a requirement for trust directly.…”

Section: Introductionmentioning

confidence: 99%

“…Its assumed potential to increase trust is one of the reasons why explainability has become a 'hot' topic in computer science and interdisciplinary research [5], and now proliferates in the RE community as a non-functional requirement [6]- [8]. Indeed, explainability and trust are often connected in the literature [5]- [72] and many researchers, at least implicitly, assume some form of what we will call the Explainability-Trust-Hypothesis (ET) in the following:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the Relation of Trust and Explainability: Why to Engineer for Trustworthiness

Kästner¹,

Langer²,

Lazar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, requirements for the explainability of software systems have gained prominence. One of the primary motivators for such requirements is that explainability is expected to facilitate stakeholders' trust in a system. Although this seems intuitively appealing, recent psychological studies indicate that explanations do not necessarily facilitate trust. Thus, explainability requirements might not be suitable for promoting trust.One way to accommodate this finding is, we suggest, to focus on trustworthiness instead of trust. While these two may come apart, we ideally want both: a trustworthy system and the stakeholder's trust. In this paper, we argue that even though trustworthiness does not automatically lead to trust, there are several reasons to engineer primarily for trustworthiness -and that a system's explainability can crucially contribute to its trustworthiness.

show abstract

Section: Future Research Directionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the Relation of Trust and Explainability: Why to Engineer for Trustworthiness

Kästner¹,

Langer²,

Lazar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…As it is considered to be a central enabler of many crucial desiderata associated with intelligent systems [5]- [7], the importance of explainability for overall system trustworthiness becomes even more apparent. These desiderata can take the form of goals, interests, needs, and demands of the multiple stakeholders involved in the development, deployment, and actual use of intelligent systems [7].…”

Section: Introductionmentioning

confidence: 99%

Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives

Langer¹,

Baum²,

Hartmann³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

National and international guidelines for trustworthy artificial intelligence (AI) consider explainability to be a central facet of trustworthy systems. This paper outlines a multidisciplinary rationale for explainability auditing. Specifically, we propose that explainability auditing can ensure the quality of explainability of systems in applied contexts and can be the basis for certification as a means to communicate whether systems meet certain explainability standards and requirements. Moreover, we emphasize that explainability auditing needs to take a multidisciplinary perspective, and we provide an overview of four perspectives (technical, psychological, ethical, legal) and their respective benefits with respect to explainability auditing.

show abstract

“…Specifically, for the case of (reasonable) trust and trustworthiness, seeKästner et al (2021). Furthermore, seeChazette et al (2021) for a general model of the impact of explainability on various social and technical phenomena.…”

mentioning

confidence: 99%

From Responsibility to Reason-Giving Explainable Artificial Intelligence

Baum

Mantel

Schmidt³

et al. 2022

Philos. Technol.

Self Cite

View full text Add to dashboard Cite

We argue that explainable artificial intelligence (XAI), specifically reason-giving XAI, often constitutes the most suitable way of ensuring that someone can properly be held responsible for decisions that are based on the outputs of artificial intelligent (AI) systems. We first show that, to close moral responsibility gaps (Matthias 2004), often a human in the loop is needed who is directly responsible for particular AI-supported decisions. Second, we appeal to the epistemic condition on moral responsibility to argue that, in order to be responsible for her decision, the human in the loop has to have an explanation available of the system’s recommendation. Reason explanations are especially well-suited to this end, and we examine whether—and how—it might be possible to make such explanations fit with AI systems. We support our claims by focusing on a case of disagreement between human in the loop and AI system.

show abstract

Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue

Cited by 59 publications

References 58 publications

On the Relation of Trust and Explainability: Why to Engineer for Trustworthiness

On the Relation of Trust and Explainability: Why to Engineer for Trustworthiness

Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives

From Responsibility to Reason-Giving Explainable Artificial Intelligence

Contact Info

Product

Resources

About