Mental Models and Causal Explanation: Judgements of Probable Cause and Explanatory Relevance

By Denis J. Hilton. 1996

Subfields: Causal Inference & Discovery, Cognitive Science & Psychology

How researchers see this paper

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

In Causal Inference & Discovery

In Cognitive Science & Psychology

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): “Hypothesis: Explanations are good if they make sense in terms of the context or the enabling conditions of cause-effect relations (Einhorn and Hogarth, 1986; Hilton and Erb, 1996).”
Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, background): “As noted by Hilton [73], discounting occurs in the context of multiple possible causes — there are several possible causes and the person is trying to determine which causes the fact —, while backgrounding occurs in the context of multiple necessary events — a subset of necessary causes is selected ”
Explaining Explanations in AI (2018, neutral): “s them irrelevant to the purposes of the explainer or recipient of an explanation (the ’explainee’). This type of selection is essential to reduce long causal chains to a cognitively manageable size (Hilton, 1996). In xAI, selection often takes the form of key features or evidence being emphasised i”
Think about it! Improving defeasible reasoning by first modeling the question scenario. (2021, background): “Mental Models Cognitive science has long promoted mental models - coherent, constructed representations of the world - as central to understanding, communication, and problem-solving (JohnsonLaird, 1983; Gentner and Stevens, 1983; Hilton, 1996).”
DREAM: Uncovering Mental Models behind Language Models (2021, background): “The concept of a mental model - a coherent, internal representation of the world - is common in cognitive science (Johnson-Laird, 1983; Gentner and Stevens, 1983; Hilton, 1996).”
Explanation and Abductive Inference (2012, background): “Potential insight into how selection occurs comes from the observation that explanations are typically contrastive: They account for one state of affairs in contrast to another (see e.g., Chin-Parker & Bradner, 2010; Garfinkel, 1990; Hart & Honore, 1985; Hilton, 1996; Hilton & Slugoski, 1986; Mackie”
BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief (2021, background): “the way the world is believed to be – as central to understanding and communication (Johnson-Laird, 1983; Gentner and Stevens, 1983; Hilton, 1996).”
Explanations in the wild. (2021, unknown): “…approach focuses on how explainers spontaneously generate relevant information given their background knowledge, whereas traditional laboratory approaches (e.g., Hilton & Erb, 1996) have tended to present participants with contrastive cases where relevance is evaluated rather than generated.”
Expanding Explainability: Towards Social Transparency in AI systems (2021, background): “This process is dynamic to the goals and changing beliefs of both parties [20, 38, 39, 45].”