AI, explain yourself

By Don Monroe. 2018

43 citations recorded by the source corpus.

It is increasingly important to understand how artificial intelligence comes to a decision.

Subfields: Artificial Intelligence

Citations in the corpus

• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “ popular press (Alang, 2017; Bornstein, 2016; Champlin, Bell, and Schocken, 2017; Clancey, 1986a; Cooper, 2004; Core, et al., 2006; Harford, 2014; Hawkins, 2017; Kim, 2018; Kuang, 2017; Marcus, 2017; Monroe, 2018; Pavlus, 2017; Nott, 2017; Pinker, 2017; Schwiep, 2017; Sheh and Monteath, 2018; Voosen”
• Computing Optimal Decision Sets with SAT (2020, neutral): “Hence the rising interest in explainable artificial intelligence (XAI) [4, 14, 16, 18, 22, 23, 26, 29, 30, 36–38, 42, 43, 48, 49, 52], including research programs [3, 24] and legislation [17, 21].”
• A review of research into automation in tourism: Launching the Annals of Tourism Research Curated Collection on Artificial Intelligence and Robotics in Tourism (2020, unknown): “Second, there is a need for designing intelligible artificial intelligence (House of Lords, 2018), making AI understandable and explainable to developers, users, and regulators (Monroe, 2018).”
• Parameterized Complexity of Small Decision Tree Learning (2021, unknown): “Because of their simplicity, decision trees are particularly attractive for providing interpretable models of the underlying data, an aspect whose importance has been stronly emphasized over the recent years (Darwiche and Hirth 2020; Doshi-Velez and Kim 2017; Goodman and Flaxman 2017; Lipton 2018; M”
• Offensive Language Detection Explained (2020, unknown): “The former refers to locally comprehending individual decisions, while the latter refers to globally comprehending the decision function (Došilović et al., 2018; Monroe, 2018; Montavon et al., 2017).”
• Towards Trustable Explainable AI (2020, unknown): “…et al. , 2018b; Katz et al. , 2017] but also motivated efforts aiming at devising approaches to ex-plainable artificial intelligence (XAI) [Ribeiro et al. , 2018; Lundberg and Lee, 2017; Ignatiev et al. , 2018; Narodytska et al. , 2018a; Ribeiro et al. , 2016; Ignatiev et al. , 2019a; Monroe, 2018].”
• Explainable AI under contract and tort law: legal incentives and technical challenges (2020, unknown): “This need for explanation—a basic human desire to learn and trust—shifts the focus away from the model and towards the explanation (Monroe 2018).”