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

arXiv: https://arxiv.org/abs/2602.03467 · HTML: https://mlsanity.com/paper/2602.03467/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 18 of 18)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Multi-shot ASP solving with clingo](https://mlsanity.com/paper/1705.09811/) (2017)
- [Concept-based Explainable Artificial Intelligence: A Survey](https://mlsanity.com/paper/2312.12936/) (2023)
- [People construct simplified mental representations to plan](https://mlsanity.com/paper/2105.06948/) (2021)
- [The Emerging Landscape of Explainable AI Planning and Decision Making](https://mlsanity.com/paper/2002.11697/) (2020)
- [On Cognitive Preferences and the Plausibility of Rule-based Models](https://mlsanity.com/paper/1803.01316/) (2018)
- [A Neuro-Symbolic ASP Pipeline for Visual Question Answering](https://mlsanity.com/paper/2205.07548/) (2022)
- [Beneficial and Harmful Explanatory Machine Learning](https://mlsanity.com/paper/2009.06410/) (2020)
- [Reliable Natural Language Understanding with Large Language Models and Answer Set Programming](https://mlsanity.com/paper/2302.03780/) (2023)
- [Answering the "why" in Answer Set Programming - A Survey of Explanation Approaches](https://mlsanity.com/paper/1809.08034/) (2018)
- [Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach](https://mlsanity.com/paper/2106.08064/) (2021)
- [Neuro-Symbolic AI for Compliance Checking of Electrical Control Panels](https://mlsanity.com/paper/2305.10113/) (2023)
- [Model Explanation via Support Graphs](https://mlsanity.com/paper/2310.01626/) (2023)
- [Abstraction for Zooming-In to Unsolvability Reasons of Grid-Cell Problems](https://mlsanity.com/paper/1909.04998/) (2019)
- [A Quantitative Symbolic Approach to Individual Human Reasoning](https://mlsanity.com/paper/2205.05030/) (2022)

## Abstract (arXiv)

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.