The hazards of explanation: overgeneralization in the face of exceptions.
By Joseph Jay Williams, Tania Lombrozo, B. Rehder. 2013
90 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Cultural Studies
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
- Tim Miller
- Gary Klein
- Robert R. Hoffman
- Shane T. Mueller
- Alon Jacovi
- William J. Clancey
- Yoav Goldberg
- Ana Marasovic
In Cultural Studies
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): “Nevertheless, it is generally acknowledged that understanding and training need to promote the transfer of concepts and principles, and good explanations should facilitate that (Lombrozo and Gwynne, 2014b; Rittle-Johnson, 2006; Williams and Lombrozo, 2010; Williams, Lombrozo, and Rehder, 2013).”
- Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, background): “It is clear that the primary function of explanation is to facilitate learning [104, 188].”
- Knowledge of animal appearance among sighted and blind adults (2019, background): “The rest is left to inferential mechanisms shared by sighted and blind people alike (22, 44, 46, 47).”
- Inference to the Best Explanation (IBE) Versus Explaining for the Best Inference (EBI) (2015, background): “, simplicity, scope), and that these criteria in turn constrain learning and inference, in part by leading people to discover and generalize the ‘‘best’’ explanation (for evidence, see Bonawitz and Lombrozo 2012; Legare and Lombrozo 2014; Lombrozo 2007; Walker et al. 2014; Williams and Lombrozo 2010”
- Aligning Faithful Interpretations with their Social Attribution (2020, background): “Plausibility should be viewed an incentive of the explainer, and not as a property of the explanation: Human explanations can be categorized by utility across multiple axes (Miller, 2019), among them are (1) learning a better internal model for future decisions and calculations (Lombrozo, 2006; Will”