![[2508.08500] Large Language Models as Oracles for Ontology Alignment](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2508.08500] Large Language Models as Oracles for Ontology Alignment
Summary
This article explores the use of Large Language Models (LLMs) as tools for improving ontology alignment, demonstrating their effectiveness in validating uncertain correspondences and achieving high performance in the Ontology Alignment Evaluation Initiative.
Why It Matters
Ontology alignment is crucial for integrating diverse data sources, and traditional methods often require extensive human input, which can be costly. By leveraging LLMs, this research offers a promising approach to enhance accuracy and efficiency in ontology mapping, potentially transforming practices in AI and data science.
Key Takeaways
- LLMs can significantly aid in the ontology alignment process by validating uncertain mappings.
- The study achieved a top-2 rank in the OAEI 2025 bio-ml track, showcasing the effectiveness of LLMs.
- A human-in-the-loop approach is essential for high-quality ontology mappings, but LLMs can reduce the need for extensive user involvement.
- Different prompt templates were tested, indicating the importance of prompt engineering in LLM performance.
- This research highlights the potential of LLMs to streamline complex AI tasks, making them more accessible.
Computer Science > Artificial Intelligence arXiv:2508.08500 (cs) [Submitted on 11 Aug 2025 (v1), last revised 15 Feb 2026 (this version, v2)] Title:Large Language Models as Oracles for Ontology Alignment Authors:Sviatoslav Lushnei, Dmytro Shumskyi, Severyn Shykula, Ernesto Jimenez-Ruiz, Artur d'Avila Garcez View a PDF of the paper titled Large Language Models as Oracles for Ontology Alignment, by Sviatoslav Lushnei and 4 other authors View PDF HTML (experimental) Abstract:There are many methods and systems to tackle the ontology alignment problem, yet a major challenge persists in producing high-quality mappings among a set of input ontologies. Adopting a human-in-the-loop approach during the alignment process has become essential in applications requiring very accurate mappings. However, user involvement is expensive when dealing with large ontologies. In this paper, we analyse the feasibility of using Large Language Models (LLM) to aid the ontology alignment problem. LLMs are used only in the validation of a subset of correspondences for which there is high uncertainty. We have conducted an extensive analysis over several tasks of the Ontology Alignment Evaluation Initiative (OAEI), reporting in this paper the performance of several state-of-the-art LLMs using different prompt templates. Using LLMs as Oracles resulted in strong performance in the OAEI 2025, achieving the top-2 overall rank in the bio-ml track. Comments: Subjects: Artificial Intelligence (cs.AI) ACM class...
