Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enriching Ontologies with Disjointness Axioms using Large Language Models

Elias Crum, Antonio De Santis, Manon Ovide, Jiaxin Pan, Alessia Pisu, Nicolas Lazzari, Sebastian Rudolph

TL;DR

This work addresses the sparsity of explicit disjointness axioms in ontologies and their impact on reasoning in knowledge graphs. It presents a satisfiability-aware, prompt-engineered LLM pipeline that identifies and asserts class disjointness, interleaving LLM guidance with logical inferences to propagate and prune disjointness while minimizing queries. Applied to the DBpedia ontology, the method discovers hundreds of thousands of disjointness assertions, which can be pruned to a more compact, consistent set, demonstrating both scalability and practical utility for automated ontology enrichment. The study highlights the potential of LLMs for ontology completion, while also documenting limitations and proposing directions for improved prompting, broader evaluation, and integration with advanced reasoning and retrieval techniques.

Abstract

Ontologies often lack explicit disjointness declarations between classes, despite their usefulness for sophisticated reasoning and consistency checking in Knowledge Graphs. In this study, we explore the potential of Large Language Models (LLMs) to enrich ontologies by identifying and asserting class disjointness axioms. Our approach aims at leveraging the implicit knowledge embedded in LLMs, using prompt engineering to elicit this knowledge for classifying ontological disjointness. We validate our methodology on the DBpedia ontology, focusing on open-source LLMs. Our findings suggest that LLMs, when guided by effective prompt strategies, can reliably identify disjoint class relationships, thus streamlining the process of ontology completion without extensive manual input. For comprehensive disjointness enrichment, we propose a process that takes logical relationships between disjointness and subclass statements into account in order to maintain satisfiability and reduce the number of calls to the LLM. This work provides a foundation for future applications of LLMs in automated ontology enhancement and offers insights into optimizing LLM performance through strategic prompt design. Our code is publicly available on GitHub at https://github.com/n28div/llm-disjointness.

Enriching Ontologies with Disjointness Axioms using Large Language Models

TL;DR

This work addresses the sparsity of explicit disjointness axioms in ontologies and their impact on reasoning in knowledge graphs. It presents a satisfiability-aware, prompt-engineered LLM pipeline that identifies and asserts class disjointness, interleaving LLM guidance with logical inferences to propagate and prune disjointness while minimizing queries. Applied to the DBpedia ontology, the method discovers hundreds of thousands of disjointness assertions, which can be pruned to a more compact, consistent set, demonstrating both scalability and practical utility for automated ontology enrichment. The study highlights the potential of LLMs for ontology completion, while also documenting limitations and proposing directions for improved prompting, broader evaluation, and integration with advanced reasoning and retrieval techniques.

Abstract

Ontologies often lack explicit disjointness declarations between classes, despite their usefulness for sophisticated reasoning and consistency checking in Knowledge Graphs. In this study, we explore the potential of Large Language Models (LLMs) to enrich ontologies by identifying and asserting class disjointness axioms. Our approach aims at leveraging the implicit knowledge embedded in LLMs, using prompt engineering to elicit this knowledge for classifying ontological disjointness. We validate our methodology on the DBpedia ontology, focusing on open-source LLMs. Our findings suggest that LLMs, when guided by effective prompt strategies, can reliably identify disjoint class relationships, thus streamlining the process of ontology completion without extensive manual input. For comprehensive disjointness enrichment, we propose a process that takes logical relationships between disjointness and subclass statements into account in order to maintain satisfiability and reduce the number of calls to the LLM. This work provides a foundation for future applications of LLMs in automated ontology enhancement and offers insights into optimizing LLM performance through strategic prompt design. Our code is publicly available on GitHub at https://github.com/n28div/llm-disjointness.
Paper Structure (13 sections, 3 theorems, 5 tables, 2 algorithms)

This paper contains 13 sections, 3 theorems, 5 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Disjointness Learning
  4. Large Language Models
  5. Prompt Engineering
  6. Resources
  7. Proposed approach
  8. Experiments
  9. Prompting
  10. Experimental setup
  11. Results
  12. Disjointness on DBpedia
  13. Conclusion and Future Work

Key Result

Proposition 1

Let $\mathcal{K}$ be a knowledge base and let $\mathtt{C}_1$, $\mathtt{C}_2$, $\mathtt{D}_1$, $\mathtt{D}_2$ be classes of $\mathcal{K}$ such that the following statements follow from $\mathcal{K}$: (i) $\mathtt{C}_1$ and $\mathtt{C}_2$ are disjoint, (ii) $\mathtt{D}_1$ is a subclass of $\mathtt{C}_

Theorems & Definitions (7)

  • Definition 1
  • Proposition 1
  • proof
  • Proposition 2
  • proof
  • Proposition 3
  • proof