paper-with-me

Papers

Can You Tell the Difference? Contrastive Explanations for ABox Entailments

2025-11-14 · Patrick Koopmann, Yasir Mahmood, Axel-Cyrille Ngonga Ngomo, Balram Tiwari 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.

📄 PDF Abstract BibTeX arXiv:2511.11281

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Rethinking Explanations: Formalizing Contrast in Description Logics

2026-05-02 · Yasir Mahmood, Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Balram Tiwari arxiv

There has been a growing interest in explaining entailments over description logic (DL) knowledge bases. The existing explanation formalisms focus on justifications to explain true axioms, and abductive reasoning to expl…

Signature-Based Abduction with Fresh Individuals and Complex Concepts for Description Logics (Extended Version)

2021-05-01 · Patrick Koopmann

Given a knowledge base and an observation as a set of facts, ABox abduction aims at computing a hypothesis that, when added to the knowledge base, is sufficient to entail the observation. In signature-based ABox abductio…

The More the Merrier: Combining Properties for ABox Abduction under Repair Semantics in ELbot

2026-06-17 · Anselm Haak, Patrick Koopmann, Yasir Mahmood, Anni-Yasmin Turhan arxiv

Abduction is a central approach to explain missing entailments from a knowledge base by providing a hypothesis, that would, if added to the knowledge base, make the missing entailment become true. Abduction under repair …

Planning Accessible Explanations for Entailments in OWL Ontologies

2012-05-01 · WS 2012 5 · Tu Anh T. Nguyen, Richard Power, Paul Piwek, S Williams 외
Text Generation

The Explabox: Model-Agnostic Machine Learning Transparency & Analysis

2024-11-22 · Marcel Robeer, Michiel Bron, Elize Herrewijnen, Riwish Hoeseni 외

We present the Explabox: an open-source toolkit for transparent and responsible machine learning (ML) model development and usage. Explabox aids in achieving explainable, fair and robust models by employing a four-step s…

DescriptiveFairness