OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion

TL;DR

OMNIA is a novel two-stage method that combines clustering, lightweight filtering, and LLM validation to improve knowledge graph completion by effectively leveraging semantic and structural information.

Contribution

It introduces a hybrid approach that bridges structural and semantic reasoning for KGC, enhancing accuracy without relying on external sources.

Findings

Significantly outperforms traditional embedding-based models in F1-score.

Reduces search space and validation cost through clustering and filtering.

Effective in completing implicit semantic triples in knowledge graphs.

Abstract

Knowledge Graphs (KGs) are widely used to represent structured knowledge, yet their automatic construction, especially with Large Language Models (LLMs), often results in incomplete or noisy outputs. Knowledge Graph Completion (KGC) aims to infer and add missing triples, but most existing methods either rely on structural embeddings that overlook semantics or language models that ignore the graph's structure and depend on external sources. In this work, we present OMNIA, a two-stage approach that bridges structural and semantic reasoning for KGC. It first generates candidate triples by clustering semantically related entities and relations within the KG, then validates them through lightweight embedding filtering followed by LLM-based semantic validation. OMNIA performs on the internal KG, without external sources, and specifically targets implicit semantics that are most frequent in LLM-generated graphs. Extensive experiments on multiple datasets demonstrate that OMNIA significantly improves F1-score compared to traditional embedding-based models. These results highlight OMNIA's effectiveness and efficiency, as its clustering and filtering stages reduce both search space and validation cost while maintaining high-quality completion.