OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion
This addresses the challenge of automatically constructing accurate knowledge graphs, which is crucial for applications relying on structured knowledge, though it appears incremental by combining existing techniques.
The paper tackles the problem of incomplete or noisy knowledge graphs by proposing OMNIA, a two-stage approach for knowledge graph completion that bridges structural and semantic reasoning, resulting in significant improvements in F1-score compared to traditional embedding-based models.
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.