Explanation Fiends and Foes: How Mechanistic Detail Determines Understanding and Preference

By Philip M. Fernbach, Steven A. Sloman, Rob St. Louis, Julia N. Shube. 2013

93 citations recorded by the source corpus.

Subfields: Applied Psychology, Cognitive Neuroscience, General Decision Sciences

How researchers see this paper

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

In Applied Psychology

In Cognitive Neuroscience

In General Decision Sciences

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, methodology): “This research has similarities to the heuristics-and-biases literature in the field of judgment and decision making, insofar as it focuses on the limitations and difficulties of understanding (see Fernbach et al., 2013; Tworek and Cimpian, 2016).”
Metrics for Explainable AI: Challenges and Prospects (2018, background): “timate how well they understand complex causal systems. This can be corrected by asking the learner to explicitly express their understanding or reasoning (Bjork et al., 2013; Chi, et al, 1989; 1991; Fernbach, et al., 2012; Mills & Keil, 2004; O’Reilly, Symons, & MacLatchy-Gaudet, 1998; Ritt”
Explaining models: an empirical study of how explanations impact fairness judgment (2019, background): “For example, research shows that some prefer simple, supericial explanations and others are more deliberative and relective in their reasoning [13, 19].”
The development and testing of a new version of the cognitive reflection test applying item response theory (irt). (2016, background): “…2014; Libearli et al., 2011; Welsh et al., 2013) but it was also related to decision-making skills (Frederick, 2005), measures of rational thinking and reasoning ability (Toplak et al., 2011; 2014), and thinking dispositions (e.g., Fernbach et al., 2013; Mata et al., 2013; Pennycook et al., 2012).”
Spotlights, Floodlights, and the Magic Number Zero: Simple Effects Tests in Moderated Regression (2012, unknown): “Fernbach et al. (2012) face these potential problems using Frederick’s (2005) cognitive reflection test, a coarse scale (four points ranging from 0 to 3) that can take on skewed distributions that vary substantially across populations.”
Assessing miserly information processing: An expansion of the Cognitive Reflection Test (2014, background): “…strategies; the avoidance of the illusion of explanatory depth; non-superstitious thinking; performance calibration, and general numeracy (Fernbach et al., 2013; Koehler & James, 2010; Liberali et al., 2012; Mata et al., 2013; Moritz et al., 2013; Oechssler et al., 2009; Pennycook et…”
Making sense of recommendations (2019, background): “And they may not truly understand the factors that influence these subjective impressions (Fernbach et al., 2012; Nisbett & Wilson, 1977; Rozenblit & Keil, 2002).”
What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research (2021, background): “The list of individual differences influencing the relation between explanatory information and understanding goes beyond the scope of this article and covers personality traits such as conscientiousness [191], need for cognition5 [192, 193], and need for closure [194, 195], as well as people’s pref”