# Can You Tell the Difference? Contrastive Explanations for ABox Entailments

arXiv: https://arxiv.org/abs/2511.11281 · HTML: https://mlsanity.com/paper/2511.11281/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 49 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 10 of 10)

- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Multi-Objective Counterfactual Explanations](https://mlsanity.com/paper/2004.11165/) (2020)
- [Contrastive Explanation: A Structural-Model Approach](https://mlsanity.com/paper/1811.03163/) (2018)
- [EvoLearner: Learning Description Logics with Evolutionary Algorithms](https://mlsanity.com/paper/2111.04879/) (2021)
- [Signature-Based Abduction for Expressive Description Logics -- Technical Report](https://mlsanity.com/paper/2007.00757/) (2020)
- [Explaining Ontology-Mediated Query Answers using Proofs over Universal Models (Technical Report)](https://mlsanity.com/paper/2208.14381/) (2022)
- [Signature-Based Abduction with Fresh Individuals and Complex Concepts for Description Logics (Extended Version)](https://mlsanity.com/paper/2105.00274/) (2021)
- [Connection-minimal Abduction in EL via Translation to FOL -- Technical Report](https://mlsanity.com/paper/2205.08449/) (2022)
- [Union and Intersection of all Justifications](https://mlsanity.com/paper/2109.11216/) (2021)
- [On the Eve of True Explainability for OWL Ontologies: Description Logic Proofs with Evee and Evonne (Extended Version)](https://mlsanity.com/paper/2206.07711/) (2022)

## Built on by (most cited first, 1 of 1)

- [Rethinking Explanations: Formalizing Contrast in Description Logics](https://mlsanity.com/paper/2605.01442/) (2026)

## Abstract (arXiv)

We introduce the notion of contrastive ABox explanations to answer questions of the type "Why is a an instance of C, but b is not?". While there are various approaches for explaining positive entailments (why is C(a) entailed by the knowledge base) as well as missing entailments (why is C(b) not entailed) in isolation, contrastive explanations consider both at the same time, which allows them to focus on the relevant commonalities and differences between a and b. We develop an appropriate notion of contrastive explanations for the special case of ABox reasoning with description logic ontologies, and analyze the computational complexity for different variants under different optimality criteria, considering lightweight as well as more expressive description logics. We implemented a first method for computing one variant of contrastive explanations, and evaluated it on generated problems for realistic knowledge bases.