Transparency: Motivations and Challenges

By Adrian Weller. 2019

174 citations recorded by the source corpus.

Subfields: Information Systems, Management Science and Operations Research, Safety Research, Safety, Robustness & Interpretability, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Management Science and Operations Research

In Safety Research

In Safety, Robustness & Interpretability

In AI Ethics, Fairness & Society

Citations in the corpus

Getting a CLUE: A Method for Explaining Uncertainty Estimates (2020, methodology): “Evaluating explanations quantitatively (without resorting to expensive user studies) is a difﬁcult but important task (Doshi-Velez & Kim, 2017; Weller, 2019).”
Explainable machine learning in deployment (2019, background): “plainabilityhasbeentoutedasawaytoenhancetransparency ofMLmodels[33].Transparencyincludesawidevarietyofeﬀorts toprovidestakeholders,particularlyendusers,withrelevantinformation about how a model works [67]. One form of this would be to publish an algorithm’s code, though this type of transparency wou”
What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research (2021, background): “Stakeholders’ desiderata are one, if not the, reason for the rising popularity of XAI (see also [14, 19]).”
Towards Explainable Artificial Intelligence (2019, background): “We refer the reader to [91] for a discussion of the challenges of transparency.”
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty (2020, background): “Transparency is one way for an artificial intelligence (AI) system to show stakeholders that the system is trustworthy [140, 183].”
The ethics of algorithms: key problems and solutions (2020, unknown): “…limits of technology or acquired by design decisions and obfuscation of the underlying data (Lepri et al. 2018; Dahl 2018; Ananny and Crawford 2018; Weller 2019)—often translates into a lack of scrutiny and/ or accountability (Oswald 2018; Fink 2018; Webb et al. 2019) and leads to a lack of…”
A Survey on the Explainability of Supervised Machine Learning (2020, background): “They pose different requirements for an explainable system due to the difference in experience and due to the different underlying goals (Weller, 2017).”
You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods (2020, background): “One motivation is to ensure fairness as part of the ‘Fair, Accountable, and Transparent’ research agenda (Diakopoulos et al. 2018; Weller 2019).”
Artificial Intelligence (AI) Student Assistants in the Classroom: Designing Chatbots to Support Student Success (2022, background): “Weller (2019) identifies eight different types of transparency for purposes of providing an explanation, with a technical explanation to the programmer being one type, and an explanation to the user (as required under the GDPR) being another type.”
Trust in AI: progress, challenges, and future directions (2024, unknown): “As a result, de ﬁ ning context-based transparency criteria is dif ﬁ cult to achieve (Weller, 2017).”
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (2019, background): “We refer the reader to [91] for a discussion of the challenges of transparency.”
Interpretable and Pedagogical Examples (2017, background): “However, there are many definitions of interpretability in the literature (Doshi-Velez & Kim, 2017; Weller, 2017; Lipton, 2016).”
Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective (2020, background): “On the technology development side, transparency is tied to explainability and high-quality documentation, but may cause harm if not compatible with the principles of privacy (Weller, 2019).”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “AI systems might start using concepts impossible to convey to humans [235,236].”