Ontology, and more broadly, Knowledge Graph Matching is a challenging task in which expressiveness has not been fully addressed. Despite the increasing use of embeddings and language models for this task, approaches for generating expressive correspondences still do not take full advantage of these models, in particular, large language models (LLMs). This paper proposes to integrate LLMs into an approach for generating expressive correspondences based on alignment need and ABox-based relation discovery. The generation of correspondences is performed by matching similar surroundings of instance sub-graphs. The integration of LLMs results in different architectural modifications, including label similarity, sub-graph matching, and entity matching. The performance word embeddings, sentence embeddings, and LLM-based embeddings, was compared. The results demonstrate that integrating LLMs surpasses all other models, enhancing the baseline version of the approach with a 45\% increase in F-measure.

In this paper, we show how to model the matching problem as a problem of joint inference. In opposite to existing ap-proaches, we distinguish between the layer of labels and the layer of concepts and properties. Entities from both layers appear as first class citizens in our model. We present an ex-ample and explain the benefits of our approach. Moreover, we argue that our approach can be extended to generate cor-respondences involving complex concept descriptions.