Explaining $\mathcal{ELH}$ Concept Descriptions through Counterfactual Reasoning

TL;DR

This paper introduces a method for generating human-friendly counterfactual explanations for concept descriptions in the description logic $ ext{ELH}$ within knowledge bases, enhancing interpretability for non-experts.

Contribution

It extends counterfactual reasoning to knowledge bases and $ ext{ELH}$, proposing a systematic approach to generate and rank minimal feature change explanations.

Findings

Counterfactual explanations are more understandable for non-experts.

The method effectively ranks counterfactuals based on feature likelihood.

User survey validates the preference for minimal and plausible counterfactuals.

Abstract

Knowledge bases are widely used for information management, enabling high-impact applications such as web search, question answering, and natural language processing. They also serve as the backbone for automatic decision systems, e.g., for medical diagnostics and credit scoring. As stakeholders affected by these decisions would like to understand their situation and verify how fair the decisions are, a number of explanation approaches have been proposed. An intrinsically transparent way to do classification is by using concepts in description logics. However, these concepts can become long and difficult to fathom for non-experts, even when verbalized. One solution is to employ counterfactuals to answer the question, ``How must feature values be changed to obtain a different classification?'' By focusing on the minimal feature changes, the explanations are short, human-friendly, and provide a clear path of action regarding the change in prediction. While previous work investigated counterfactuals for tabular data, in this paper, we transfer the notion of counterfactuals to knowledge bases and the description logic $\mathcal{ELH}$. Our approach starts by generating counterfactual candidates from concepts, followed by selecting the candidates requiring the fewest feature changes as counterfactuals. When multiple counterfactuals exist, we rank them based on the likeliness of their feature combinations. We evaluate our method by conducting a user survey to determine which counterfactual candidates participants prefer for explanation.