Abstract Standard articulations of Inference to the Best Explanation (IBE) imply uniqueness claim that exactly one explanation should be inferred in response an explanandum. This has been challenged as being both too strong (sometimes agnosticism between candidate explanatory hypotheses seems rational conclusion) and weak (in cases where multiple might sensibly conjointly inferred). I propose a...

In automated planning, the need for explanations arises when there is a mismatch between proposed plan and user’s expectation. We frame Explainable AI Planning as an iterative exploration process, in which user asks succession of contrastive questions that lead to generation solution hypothetical planning problems are restrictions original problem. The object understand constraints govern and, ...

Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks arisen as explainable-by-design methods they leverage human-understandable symbols (i.e. concepts) to predict class memberships. However, most of these approaches focus on the identification relevant concepts but do not pr...

is provided in screen-viewable form for personal use only by members of MIT CogNet. Unauthorized use or dissemination of this information is expressly forbidden. If you have any questions about this material, please contact [email protected].

We present a new experimental investigation of preference reversal. Although economists and psychologists have suggested a variety of accounts for this phenomenon, the existing data do not adequately discriminate between them. Relative to previous studies, our design offers enhanced control for economic explanations and new tests of psychological hypotheses. We find a pattern of preference reve...

Explaining how engineering devices work is important to students, engineers, and operators. In general, machine generated explanations have been produced from a particular perspective. This paper introduces a system called automatic generation of explanations (AGE) capable of generating causal, behavioral, and functional explanations of physical devices in natural language. AGE explanations can...