The Dual Role of Abstracting over the Irrelevant in Symbolic Explanations: Cognitive Effort vs. Understanding

Abstract

Explanations are central to human cognition, yet AI systems often produce outputs that are difficult to understand. While symbolic AI offers a transparent foundation for interpretability, raw logical traces often impose a high extraneous cognitive load. We investigate how formal abstractions, specifically removal and clustering, impact human reasoning performance and cognitive effort. Utilizing Answer Set Programming (ASP) as a formal framework, we define a notion of irrelevant details to be abstracted over to obtain simplified explanations. Our cognitive experiments, in which participants classified stimuli across domains with explanations derived from an answer set program, show that clustering details significantly improve participants' understanding, while removal of details significantly reduce cognitive effort, supporting the hypothesis that abstraction enhances human-centered symbolic explanations.

Questions this source addresses

• How can Answer Set Programming be used to formally define which details in a logical trace are 'irrelevant' and thus eligible for abstraction in an explanation?
• How do removal and clustering, as two distinct abstraction operations over irrelevant details in symbolic explanations, differ in their effects on human understanding versus cognitive effort?
• What does the finding that clustering improves understanding while removal reduces cognitive effort imply for designing human-centered explanations from symbolic AI systems?
• What experimental methodology was used to measure participants' reasoning performance and extraneous cognitive load when classifying stimuli using ASP-derived explanations?