IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment

arXiv:2607.25579v1 Announce Type: new Abstract: Entity alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object. Conventional EA methods mainly exploit explicit graph structures and textual fields, which often provide insufficient semantic understanding to recognize the same entity under heterogeneous descriptions and distinguish it from semantically similar entities. Although large language models (LLMs) offer deeper entity understanding, existin...