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

2026-03-12

AI Summary

This work addresses the limitations of current knowledge graph completion methods, which often suffer from missing facts or noise introduced by large language model (LLM) generation and struggle to jointly leverage structural and semantic information. To overcome these challenges, the authors propose OMNIA, a two-stage, self-contained completion approach that requires no external resources. In the first stage, candidate triples are generated via entity-relation clustering; in the second, a lightweight graph embedding module filters candidates, followed by LLM-based semantic validation—all relying solely on internal graph information. OMNIA is the first method to synergistically combine structural clustering with LLM-driven semantic verification for implicit completion of LLM-generated knowledge graphs. Experiments demonstrate significant F1 score improvements across multiple datasets, alongside a substantial reduction in both search space and verification cost.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• Knowledge Graph Completion
• Large Language Models
• Semantic Reasoning
• Structural Embeddings
• Implicit Semantics

Innovation

• Knowledge Graph Completion
• Large Language Models
• Semantic Clustering
• Structural Embedding
• LLM-based Validation