The Instrumental Value of Explanations

By Tania Lombrozo. 2011

104 citations recorded by the source corpus.

Subfields: Artificial Intelligence, History and Philosophy of Science, Molecular Biology

How researchers see this paper

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

In Artificial Intelligence

In History and Philosophy of Science

In Molecular Biology

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, background): “…2017; Gopnik, 2000; Kass and Leake, 1987; Keil, 2006; Keil, Rozenblit, and Mills, 2004; Koehler, 1991; Kuhn, 2001; Leddo, Abelson, and Gross, 1984; Lombrozo, 2006, 2009a, 2011, 2016; Lombrozo and Carey, 2006; Lombrozo and Gwynne, 2014a; Lombrozo, Sloman, Strevens, Trout, and Skolnick Weisberg,…”
RISE: Randomized Input Sampling for Explanation of Black-box Models (2018, background): “There is extensive evidence for the importance of explanation towards understanding and building trust in cognitive psychology [1], philosophy [2] and machine learning [3, 4, 5] research.”
Expanding Explainability: Towards Social Transparency in AI systems (2021, background): “On one hand, explanations (as a construct) are socially situated [64, 65, 70, 105].”
Representing, Running, and Revising Mental Models: A Computational Model (2018, methodology): “The cognitive science literature has characterized factors that impact people’s judgments of explanations, including causal simplicity, coverage of observations, goal appeal, and narrative structure (Lombrozo, 2011).”
FOLK ATTRIBUTIONS OF UNDERSTANDING: IS THERE A ROLE FOR EPISTEMIC LUCK? (2016, background): “understanding is about trust and deference—a connection espoused by Rosenberg (1981) and defended empirically in Wilkenfeld, Plunkett, and Lombrozo (2016)—one might expect understanders to have a particularly robust relationship to the truth.”
What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research (2021, background): “Explanatory information helps humans to navigate complex environments by facilitating better understanding, predictions, and control of situations [138, 174].”
Contrastive Constraints Guide Explanation-Based Category Learning (2017, background): “Work examining the role of explanation in learning has focused on the mechanisms involved in developing the relevant knowledge (Chi, 2000) and how the knowledge generated via explanation may provide a foundation for future generalizations (Lombrozo, 2011; Lombrozo & Carey, 2006).”