Explanatory Preferences Shape Learning and Inference.

By Tania Lombrozo. 2016

185 citations recorded by the source corpus.

Subfields: Developmental and Educational Psychology, 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 Developmental and Educational Psychology

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): “cord, 1983; McClure, 2002; McClure and Hilton, 1997, 1998; McClure, Sutton, and Hilton, 2003; Malle, 1999, 2004, 2011; Rey, 2012; Royce, 1963; Sloman, 1994; Swartout, 1987; Vasilyeva, Wilkenfeld, and Lombrozo, 2016; Vasilyeva and Lombrozo, 2015) Social Psychology One focus of explanation has been on”
Metrics for Explainable AI: Challenges and Prospects (2018, background): “Selfgenerated deductions and generalizations help learners refine their knowledge (Chi and VanLehn, 1991: Chi, et al, 1989, 1994; Chi & Van Lehn, 1991; Lombrozo, 2016; Molinaro & Garcia-Madruga, 2011; Rittle-Johnson, 2006).”
Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics (2021, background): “Lombrozo [30] showed that explanations considered good are simple and broad.”
A historical perspective of explainable Artificial Intelligence (2020, background): “…the criteria for a good explanation as of today is an active debate in various fields, including cognitive science, computer science, psychology, and philosophy (Confalonieri et al., 2019; Guidotti et al., 2018; Hoffman, Mueller, Klein, & Litman, 2018; Lipton, 2018; Lombrozo, 2016; Miller, 2019).”
Explanation-seeking curiosity in childhood (2020, background): “Seeking explanations supports learning in young children [10,11], and explanations can drive subsequent exploration [12] and improve”
Artificial intelligence and illusions of understanding in scientific research (2024, unknown): “Experiments show people prefer answers and explanations that are simple 96,97 , broad 96,98,99 , reductive 100–102 and quantitative 103,104 .”
Question-asking in childhood: A review of the literature and a framework for understanding its development (2018, background): “Furthermore, they are also able to adapt their question-asking strategy based on task characteristics, such as the information structure of a task (for example, whether or not the hypotheses being considered are equally likely), and the feedback they receive from people about their questions (Rugger”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap (2023, background): “…information. p This goal-oriented perspective resonates with studies of human explanations from cognitive science, philosophy, and psychology (Lombrozo, 2016; Miller, 2019), where it is recognized that seeking explanations and achieving understanding is often a means to an end for downstream…”