CMOMgen: Complex multi-ontology alignment via pattern-guided in-context learning

Constructing comprehensive knowledge graphs requires the use of multiple ontologies in order to fully contextualize data into a domain. Ontology matching finds relationships between concepts interconnecting ontologies and creating a cohesive semantic layer. While the simple equivalence pairwise state of the art is well established, these simple mappings cannot provide full semantic integration of related but disjoint ontologies. Complex multi-ontology matching (CMOM) aligns three or more ontologies using composite logical expressions or transformations , establishing more nuanced connections and provenance along the ontological hierarchy. We present CMOMgen, the first end-to-end CMOM strategy that generates complete and semantically sound 1:n multi-ontology complex equivalence mappings, without establishing any restrictions on the number of target ontologies or entities. Retrieval-Augmented Generation selects relevant classes to compose the mapping and filters reference mappings to serve as examples to guide In-Context Learning in generating complex OWL expressions . The strategy was evaluated in three biomedical tasks with partial reference alignments, demonstrating consistent performance across settings, with a minimum F1-score of 63%. In addition , a manual evaluation of non-reference mappings showed that 46% of the mappings achieve the maximum score, further substantiating its ability to construct accurate, high-fidelity mappings.