Quo Vadis, Explainability? – A Research Roadmap for Explainability Engineering

Brunotte, Wasja; Chazette, Larissa; Klös, Verena; Speith, Timo

doi:10.1007/978-3-030-98464-9_3

Cited by 15 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problems that XAI should tackle often require interdisciplinary research [17,41,44]. Preventing discrimination [24,41,74], increasing trustworthiness [37,41,46], allocating responsibility [13,41,59], and generally, promoting human well-being [27,46] is, in principle, possible with explainability -as long as researchers from different disciplines can come together to work on it.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Taxonomies of Explainable Artificial Intelligence (XAI) Methods

Speith

2022

2022 ACM Conference on Fairness, Accountability, and Transparency

Self Cite

135

View full text Add to dashboard Cite

The recent surge in publications related to explainable artificial intelligence (XAI) has led to an almost insurmountable wall if one wants to get started or stay up to date with XAI. For this reason, articles and reviews that present taxonomies of XAI methods seem to be a welcomed way to get an overview of the field. Building on this idea, there is currently a trend of producing such taxonomies, leading to several competing approaches to construct them. In this paper, we will review recent approaches to constructing taxonomies of XAI methods and discuss general challenges concerning them as well as their individual advantages and limitations. Our review is intended to help scholars be aware of challenges current taxonomies face. As we will argue, when charting the field of XAI, it may not be sufficient to rely on one of the approaches we found. To amend this problem, we will propose and discuss three possible solutions: a new taxonomy that incorporates the reviewed ones, a database of XAI methods, and a decision tree to help choose fitting methods. CCS CONCEPTS• General and reference → Surveys and overviews; • Computing methodologies → Artificial intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Additionally, the plug-and-play nature of the conceptual approach, which allows for adding dimensions as desired, is especially wellsuited for creating taxonomies that are fit for specific purposes. For these reasons, this approach is likely a good starting point when it comes to (more advanced) interdisciplinary work [17,41,44].…”

Section: 23mentioning

confidence: 99%

A Review of Taxonomies of Explainable Artificial Intelligence (XAI) Methods

Speith

2022

2022 ACM Conference on Fairness, Accountability, and Transparency

Self Cite

135

View full text Add to dashboard Cite

show abstract

“…Furthermore, a large body of research was done in terms of privacy policies and how to communicate them in a more comprehensible way to end users [79,80,20,81,82,83,84,85].…”

Section: Related Workmentioning

confidence: 99%

“…Building upon findings of our research, we need to investigate how to translate our set of requirements for privacy explanations into a system. To keep privacy explanations as simple as possible in order not to overwhelm the user, we plan a user study in which we survey how privacy explanation must be engineered [79]. We assume, that an hierarchical information structure may be beneficial.…”

Section: Future Directionsmentioning

confidence: 99%

Privacy explanations – A means to end-user trust

Brunotte

Specht

Chazette

et al. 2023

Journal of Systems and Software

View full text Add to dashboard Cite

“…A useful explanation should be easily understood by humans, but (in contrast to other software) autonomous systems may make surprising decisions, which means that useful explanations are not always obvious. To design effective explainability, one must know the system's stakeholders and context: to whom are you explaining, and what the system will be doing [14].…”

Section: Designing Explainabilitymentioning

confidence: 99%

An Abstract Architecture for Explainable Autonomy in Hazardous Environments

Luckcuck

Taylor

Farrell

2022

2022 IEEE 30th International Requirements Engineering Conference Workshops (REW)

View full text Add to dashboard Cite

Autonomous robotic systems are being proposed for use in hazardous environments, often to reduce the risks to human workers. In the immediate future, it is likely that human workers will continue to use and direct these autonomous robots, much like other computerised tools but with more sophisticated decision-making. Therefore, one important area on which to focus engineering effort is ensuring that these users trust the system. Recent literature suggests that explainability is closely related to how trustworthy a system is. Like safety and security properties, explainability should be designed into a system, instead of being added afterwards. This paper presents an abstract architecture that supports an autonomous system explaining its behaviour (explainable autonomy), providing a design template for implementing explainable autonomous systems. We present a worked example of how our architecture could be applied in the civil nuclear industry, where both workers and regulators need to trust the system's decision-making capabilities.

show abstract

Quo Vadis, Explainability? – A Research Roadmap for Explainability Engineering

Cited by 15 publications

References 13 publications

A Review of Taxonomies of Explainable Artificial Intelligence (XAI) Methods

A Review of Taxonomies of Explainable Artificial Intelligence (XAI) Methods

Privacy explanations – A means to end-user trust

An Abstract Architecture for Explainable Autonomy in Hazardous Environments

Contact Info

Product

Resources

About