Publications · International Semantic Web Conference (ISWC), 2025
KROMA: Ontology Matching with Knowledge Retrieval and Large Language Models
TL;DR An LLM decides whether two concepts from different ontologies mean the same thing, given context retrieved from their structure, labels, and definitions. Bisimilarity pruning and incremental refinement keep the number of LLM calls low.
Read the full version arXiv PDF Paper (Springer) Code Manual
Highlights
- Highest F1 on all six OAEI-style tracks against MILA, OLaLa, and LLM4OM, for example 98.63 on NCIT–DOID and 94.94 on Mouse–Human.
- Removing knowledge retrieval or ontology refinement lowers F1 on every track reported.
Abstract
Ontology Matching (OM) is a cornerstone task of semantic interoperability, yet existing systems often rely on handcrafted rules or specialized models with limited adaptability. We present KROMA, a novel OM framework that harnesses Large Language Models (LLMs) within a Retrieval-Augmented Generation (RAG) pipeline to dynamically enrich the semantic context of OM tasks with structural, lexical, and definitional knowledge. To optimize both performance and efficiency, KROMA integrates a bisimilarity-based concept matching and a lightweight ontology refinement step, which prune candidate concepts and substantially reduce the communication overhead from invoking LLMs. Through experiments on multiple benchmark datasets, we show that integrating knowledge retrieval with context-augmented LLMs significantly enhances ontology matching, outperforming both classic OM systems and cutting-edge LLM-based approaches while keeping communication overhead comparable. Our study highlights the feasibility and benefit of the proposed optimization techniques (targeted knowledge retrieval, prompt enrichment, and ontology refinement) for ontology matching at scale.
Read
On a phone, open the PDF in your browser's reader.
Cite
@inproceedings{nguyen_2025_kroma,
title={KROMA: Ontology Matching with Knowledge Retrieval and Large Language Models},
author={Lam Nguyen and Erika Barcelos and Roger French and Yinghui Wu},
booktitle={The Semantic Web -- ISWC 2025},
series={Lecture Notes in Computer Science},
publisher={Springer},
pages={629--649},
year={2025},
doi={10.1007/978-3-032-09527-5_34},
}