Explainability as a Non-Functional Requirement

Köhl, Maximilian A.; Baum, Kevin; Langer, Markus; Oster, Daniel; Speith, Timo; Bohlender, Dimitri

doi:10.1109/re.2019.00046

Cited by 63 publications

(60 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Throughout the history of XAI research, authors have highlighted the central importance of understanding in XAI (e.g., [2,20,115,[140][141][142]). The overall goal of XAI is to advance human understanding of artificial systems in order to satisfy a given desideratum.…”

Section: Understandingmentioning

confidence: 99%

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

Langer

Oster

Speith

et al. 2021

Artificial Intelligence

Self Cite

292

191

View full text Add to dashboard Cite

Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding artificial systems (we call these 'stakeholders' desiderata') in a variety of contexts. However, the literature on XAI is vast, spreads out across multiple largely disconnected disciplines, and it often remains unclear how explainability approaches are supposed to achieve the goal of satisfying stakeholders' desiderata. This paper discusses the main classes of stakeholders calling for explainability of artificial systems and reviews their desiderata.

show abstract

Section: Understandingmentioning

confidence: 99%

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

Langer

Oster

Speith

et al. 2021

Artificial Intelligence

Self Cite

292

191

View full text Add to dashboard Cite

show abstract

“…Their goal is to understand requirements for XAI from multiple perspectives, assess explanation capabilities, and steer future research to industrial cases. In [48], also inspired by the requirements engineering literature, the authors propose a workflow to elucidate requirements for explanations, considering those requirements are non-functional. The methodology is assessed in a hypothetical hiring scenario.…”

Section: Related Workmentioning

confidence: 99%

Scenario-Based Requirements Elicitation for User-Centric Explainable AI

Cirqueira

Nedbal

Helfert

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) develops technical explanation methods and enable interpretability for human stakeholders on why Artificial Intelligence (AI) and machine learning (ML) models provide certain predictions. However, the trust of those stakeholders into AI models and explanations is still an issue, especially domain experts, who are knowledgeable about their domain but not AI inner workings. Social and user-centric XAI research states it is essential to understand the stakeholder's requirements to provide explanations tailored to their needs, and enhance their trust in working with AI models. Scenariobased design and requirements elicitation can help bridge the gap between social and operational aspects of a stakeholder early before the adoption of information systems and identify its real problem and practices generating user requirements. Nevertheless, it is still rarely explored the adoption of scenarios in XAI, especially in the domain of fraud detection to supporting experts who are about to work with AI models. We demonstrate the usage of scenario-based requirements elicitation for XAI in a fraud detection context, and develop scenarios derived with experts in banking fraud. We discuss how those scenarios can be adopted to identify user or expert requirements for appropriate explanations in his daily operations and to make decisions on reviewing fraudulent cases in banking. The generalizability of the scenarios for further adoption is validated through a systematic literature review in domains of XAI and visual analytics for fraud detection.

show abstract

“…Therefore, the artifact must provide sufficient explanations for each recommendation (M6a). Explanations must be adapted to stakeholders [63]. At the same time, a patient may be satisfied with a recommendation and indicators for how their preferences were considered and will be realized by a recommendation, a healthcare professional demands further details such as the specific interplay of components of drugs.…”

Section: ] (M1b)mentioning

confidence: 99%

Towards a Reference Architecture for Female-Sensitive Drug Management

Mateja

Bartels²,

Oberste³

et al. 2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Due to various biological factors, males and females differ in their response to drug treatment. However, there is still a lack of knowledge of the effects resulting from sex-differences in the medical field, primarily due to females' underrepresentation in clinical studies. Considering severe diseases related to the cardiovascular system, which are likely to be perilous, counteracting this lack and emphasizing the need for sex-dependent drug treatment is of high importance. Thus, this research-in-progress paper aims to strengthen the female perspective in drug management by proposing design considerations on IS regarding recommender systems in healthcare to reinforce shared decision-making and person-centered care. The resulting artifact presented will be a reference architecture with a mobile application as the interface to patients and healthcare professionals as well as a data-driven backend to collect and process data on sex specificity in the medical treatment of cardiovascular diseases (CVD).

show abstract

Explainability as a Non-Functional Requirement

Cited by 63 publications

References 23 publications

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

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

Scenario-Based Requirements Elicitation for User-Centric Explainable AI

Towards a Reference Architecture for Female-Sensitive Drug Management

Contact Info

Product

Resources

About