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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ieng, Frédéric, Sahri, Soror, Ouzzani, Mourad, Hammaz, Massinissa, Benbernou, Salima, Khorashadizadeh, Hanieh, Groppe, Sven, Benamara, Farah
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912965608865792
author Ieng, Frédéric
Sahri, Soror
Ouzzani, Mourad
Hammaz, Massinissa
Benbernou, Salima
Khorashadizadeh, Hanieh
Groppe, Sven
Benamara, Farah
author_facet Ieng, Frédéric
Sahri, Soror
Ouzzani, Mourad
Hammaz, Massinissa
Benbernou, Salima
Khorashadizadeh, Hanieh
Groppe, Sven
Benamara, Farah
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11820
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion
Ieng, Frédéric
Sahri, Soror
Ouzzani, Mourad
Hammaz, Massinissa
Benbernou, Salima
Khorashadizadeh, Hanieh
Groppe, Sven
Benamara, Farah
Databases
Artificial Intelligence
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.
title OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2603.11820