Challenges for Transparency

By Adrian Weller. 2017

123 citations recorded by the source corpus.

Transparency is often deemed critical to enable effective real-world deployment of intelligent systems. Yet the motivations for and benefits of different types of transparency can vary significantly depending on context, and objective measurement criteria are difficult to identify. We provide a brief survey, suggesting challenges and related concerns. We highlight and review settings where transparency may cause harm, discussing connections across privacy, multi-agent game theory, economics, fairness and trust.

Subfields: AI Ethics, Fairness & Society, Human-Computer Interaction

How researchers see this paper

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

In AI Ethics, Fairness & Society

In Human-Computer Interaction

Citations in the corpus

On the Art and Science of Machine Learning Explanations (2018, background): “s have previously defined key terms, put forwardgeneralmotivationsforthebroadergoalofbetterinterpretability, and advocated for stronger scientific rigor for the burgeoning field [6], [9], [11], [15], [23]. Following Doshi-Velez and Kim, this discussion uses “the ability to explain or to present in u”
Learning Optimal Decision Trees with SAT (2018, background): “Furthermore, the relevance of XAI is implicit in recent EU-level regulations [EU Data Protection Regulation, 2016], which is motivated in part by a demand for greater transparency in algorithmic decision making [Goodman and Flaxman, 2017; Weller, 2017].”
Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, methodology): “This information is then used to assess the appropriateness of the outcome in relation to the concerns and values of users (Doran et al., 2017; Wachter et al., 2017; Doshi-Velez et al., 2017; Weller, 2017).”
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values (2018, background): “Given increasing reliance on local model explanations for decision making, it is important to assess explanation quality, and characterize their ﬁdelity to the model being explained (Doshi-Velez & Kim, 2017; Weller, 2017).”
A Survey of Methods for Explaining Black Box Models (2018, background): “Many questions feed the papers in the literature proposing methodologies for interpreting black box systems [106,34]: What”
Explaining Explanations in AI (2018, neutral): “Justification has recently received increasing attention by scholars discussing algorithmic accountability (e.g. Binns (2017); Biran and McKeown (2014); Hildebrandt and Koops (2010); Selbst and Barocas (2018); Weller (2017)).”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “The potential for local, pedagogical explanation systems to provide justice-related information, fulfilling the policy goals of transparency, accountability and fairness, has recently been noted by computer scientists and law scholars [20, 65, 82].”
Auditing large language models: a three-layered approach (2023, methodology): “Alternative techniques that are better suited for developing truthful AI include bootstrapping, adversarial training [202] and transparent AI [203].”
Questioning the AI: Informing Design Practices for Explainable AI User Experiences (2020, background): “Although this is not uncommon for studies of practitioners [7, 32, 67] and we recruited informants from diverse product lines and locations, we acknowledge that design practices may be different in other companies or organizations.”
Transparency you can trust: Transparency requirements for artificial intelligence between legal norms and contextual concerns (2019, background): “The work from Weller (2017), however, does not include diﬀerent types of users within each stakeholder group such as secondary or disabled users.”
Transparency: Motivations and Challenges (2017, background): “cs and the social sciences, philosophy, multi-agent game theory, law, policy and cognitive science. Transparency: Motivations and Challenges 15 Acknowledgements This article is an extended version of [71]. The author thanks Frank Kelly for pointing out the Braess’ paradox example and related intuiti”
Transparency: Motivations and Challenges (2019, background): “This article is an extended version of [71].”