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

Langer, Markus; Baum, Kevin; Hartmann, Kathrin; Hessel, Stefan; Speith, Timo; Wahl, Jonas

doi:10.1109/rew53955.2021.00030

Cited by 11 publications

(10 citation statements)

References 26 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. Accordingly, confusion in the field may postpone the potentially vast social benefits XAI promises to bring about.…”

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%

“…Another factor that might contribute to the emergence of cases that our proposals do not cover is that vital dimensions are missing. We will illustrate this idea by means of the dimension fidelity [41].…”

Section: New Dimensions For the Taxonomymentioning

confidence: 99%

“…By understanding how a particular system's output (e.g., a denied loan decision) came to be, a person should be enabled to assess whether this output was based on valid criteria or not [29,57]. If, for instance, an unfavorable decision was based on (a proxy for) the skin color of a person, this person should be able to recognize that they were treated unfairly [19,41].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Speith

2022

2022 ACM Conference on Fairness, Accountability, and Transparency

Self Cite

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%

Section: 23mentioning

confidence: 99%

Section: New Dimensions For the Taxonomymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Speith

2022

2022 ACM Conference on Fairness, Accountability, and Transparency

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this regard, explainability is increasingly seen as the preferred solution to mitigate a system's lack of transparency [5] and as a fruitful way to address ethical concerns about modern systems [6]. The concept of explainability has received a lot of attention recently, and it is slowly…”

Section: Explainability As the Solutionmentioning

confidence: 99%

Explainable software systems: from requirements analysis to system evaluation

2022

Self Cite

View full text Add to dashboard Cite

The growing complexity of software systems and the influence of software-supported decisions in our society sparked the need for software that is transparent, accountable, and trustworthy. Explainability has been identified as a means to achieve these qualities. It is recognized as an emerging non-functional requirement (NFR) that has a significant impact on system quality. Accordingly, software engineers need means to assist them in incorporating this NFR into systems. This requires an early analysis of the benefits and possible design issues that arise from interrelationships between different quality aspects. However, explainability is currently under-researched in the domain of requirements engineering, and there is a lack of artifacts that support the requirements engineering process and system design. In this work, we remedy this deficit by proposing four artifacts: a definition of explainability, a conceptual model, a knowledge catalogue, and a reference model for explainable systems. These artifacts should support software and requirements engineers in understanding the definition of explainability and how it interacts with other quality aspects. Besides that, they may be considered a starting point to provide practical value in the refinement of explainability from high-level requirements to concrete design choices, as well as on the identification of methods and metrics for the evaluation of the implemented requirements.

show abstract