Explainable AI: The New 42?

Goebel, Randy; Chander, Ajay; Holzinger, Katharina; Lécué, Freddy; Akata, Zeynep; Stumpf, Simone; Kieseberg, Peter; Holzinger, Andreas

doi:10.1007/978-3-319-99740-7_21

Cited by 204 publications

(91 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While in some domains automation is relevant, it is essential for others to understand AI predictions and decisions for human stakeholders [10], as explanations can impact the work of stakeholders who adopt such tools for decision-making [12]. For instance, in healthcare, doctors can adopt explanation methods to understand the diagnosis provided by AI models predictions [10].…”

Section: Introductionmentioning

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

Section: Introductionmentioning

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

show abstract

“…Even though the concept of algorithm "transparency" is as old as recommendation systems, the emergence and the ubiquity of "black-box" learning algorithms nowadays, such as neural networks, put "transparency" of algorithms back in the limelight [14]. As detailed in Sect.…”

Section: Definition Of a "Transparent" Classification Systemmentioning

confidence: 99%

Transparency of Classification Systems for Clinical Decision Support

Richard

Mayag

Talbot

et al. 2020

Information Processing and Management of Uncertainty in Knowledge-Based Systems

View full text Add to dashboard Cite

In collaboration with the Civil Hospitals of Lyon, we aim to develop a "transparent" classification system for medical purposes. To do so, we need clear definitions and operational criteria to determine what is a "transparent" classification system in our context. However, the term "transparency" is often left undefined in the literature, and there is a lack of operational criteria allowing to check whether a given algorithm deserves to be called "transparent" or not. Therefore, in this paper, we propose a definition of "transparency" for classification systems in medical contexts. We also propose several operational criteria to evaluate whether a classification system can be considered "transparent". We apply these operational criteria to evaluate the "transparency" of several well-known classification systems.

show abstract

“…Thus, there is room for experts from different fields, including linguists, to identify sound and practical solutions, but interactive machine learning could also be of help here. Moreover, verbal explanations are extremely important for the emerging field of "explainable artificial intelligence" (Goebel et al 2018), which opens additional application fields.…”

Section: Linguistic Qualitymentioning

confidence: 99%

Augmenting Statistical Data Dissemination by Short Quantified Sentences of Natural Language

Hudec

Bednárová

Holzinger³

2018

Journal of Official Statistics

Self Cite

View full text Add to dashboard Cite

Data from National Statistical Institutes is generally considered an important source of credible evidence for a variety of users. Summarization and dissemination via traditional methods is a convenient approach for providing this evidence. However, this is usually comprehensible only for users with a considerable level of statistical literacy. A promising alternative lies in augmenting the summarization linguistically. Less statistically literate users (e.g., domain experts and the general public), as well as disabled people can benefit from such a summarization. This article studies the potential of summaries expressed in short quantified sentences. Summaries including, for example, “most visits from remote countries are of a short duration” can be immediately understood by diverse users. Linguistic summaries are not intended to replace existing dissemination approaches, but can augment them by providing alternatives for the benefit of diverse users of official statistics. Linguistic summarization can be achieved via mathematical formalization of linguistic terms and relative quantifiers by fuzzy sets. To avoid summaries based on outliers or data with low coverage, a quality criterion is applied. The concept based on linguistic summaries is demonstrated on test interfaces, interpreting summaries from real municipal statistical data. The article identifies a number of further research opportunities, and demonstrates ways to explore those.

show abstract

Explainable AI: The New 42?

Cited by 204 publications

References 15 publications

Scenario-Based Requirements Elicitation for User-Centric Explainable AI

Scenario-Based Requirements Elicitation for User-Centric Explainable AI

Transparency of Classification Systems for Clinical Decision Support

Augmenting Statistical Data Dissemination by Short Quantified Sentences of Natural Language

Contact Info

Product

Resources

About