Explanation and understanding

By A. Sora. 2015

Subfields: Safety, Robustness & Interpretability

How researchers see this paper

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

In Safety, Robustness & Interpretability

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): “Keil, 2006 Review of studies on the benefits of explanation, in research with laypersons, college students, and children as participants.”
Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, background): “ranging from dialogues for pragmatic explanation [132] to definitions based on transfer of understanding [134].”
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, background): “Human explanations typically appeal to causal structure [Lombrozo, 2006] and counterfactuals [Keil, 2006].”
Causal Induction from Visual Observations for Goal Directed Tasks (2019, unknown): “M ANY (Common Cause (Keil, 2006)), where all lights are controlled by at most one switch, but a single switch may control more than one light.”
Asking 'Why' in AI: Explainability of intelligent systems - perspectives and challenges (2018, background): “, scientific explanations), and cultural schemas (Keil, 2006).”
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 importance of acknowledging the characteristics of explanatory information is highlighted by research in cognitive and educational psychology that shows that effects of explanatory information can vary depending on their characteristics [138, 150, 166].”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap (2023, background): “…cognitive science, and HCI, there is a long tradition of breaking down different types of explanations by their mechanism, stance, and the questions that they answer (e.g., what, how, why, why not, what if) (Graesser et al., 1996; Hilton, 1990; Keil, 2006; Liao et al., 2020; Lombrozo, 2012, 2016).”
Cognitive foundations for science assessment design: Knowing what students know about evolution (2012, background): “…explanations of evolutionary change—rather than descriptions—are highly useful for probing student’s causal understanding of evolutionary change because students typically expect that good explanations should mention causally central information (Callanan & Oakes, 1992; Keil, 2006; Lombrozo, 2006).”
The role of emotion in self-explanations by cognitive agents (2017, background): “When provided in a social setting, emotions and motivations increase the acceptance of human action explanations [20].”
Self-Explaining Agents in Virtual Training (2008, background): “Such explanations can become quite long, which is not desired [7].”
Argumentation for Learning: Well-Trodden Paths and Unexplored Territories (2016, background): “Second, given that argumentation and explanation are two different epistemic dialogue acts (de Vries, Lund, & Baker, 2002; Keil, 2006; Walton, 2006), they are likely to reflect and to stimulate different (socio-) cognitive processes.”
Towards A Rigorous Science of Interpretable Machine Learning (2017, background): “Keil [2006] considered a broader deﬁnition: implicit explanatory understanding.”
Evaluating everyday explanations (2017, background): “there are gaps in the causal structure (Keil, 2006).”
Definitions, methods, and applications in interpretable machine learning (2019, background): “In psychology, the general notions of interpretability and explanations have been studied at a more abstract level (17, 18), providing relevant conceptual perspectives.”