Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Graph Fusion Across Languages using Large Language Models

Kaung Myat Kyaw, Khush Agarwal, Jonathan Chan

Abstract

Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the in-context reasoning and multilingual semantic priors of Large Language Models (LLMs). The framework implements structural linearization by mapping triplets directly into natural language sequences (e.g., [head] [relation] [tail]), enabling the LLM to map relations and reconcile entities between an evolving fused graph ($G_{c}^{(t-1)}$) and a new candidate graph ($G_{t}$). Evaluated on the DBP15K dataset, this exploratory study demonstrates that LLMs can serve as a universal semantic bridge to resolve cross-lingual discrepancies. Results show the successful sequential agglomeration of multiple heterogeneous graphs, offering a scalable, modular solution for continuous knowledge synthesis in multi-source, multilingual environments.

Graph Fusion Across Languages using Large Language Models

Abstract

Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the in-context reasoning and multilingual semantic priors of Large Language Models (LLMs). The framework implements structural linearization by mapping triplets directly into natural language sequences (e.g., [head] [relation] [tail]), enabling the LLM to map relations and reconcile entities between an evolving fused graph () and a new candidate graph (). Evaluated on the DBP15K dataset, this exploratory study demonstrates that LLMs can serve as a universal semantic bridge to resolve cross-lingual discrepancies. Results show the successful sequential agglomeration of multiple heterogeneous graphs, offering a scalable, modular solution for continuous knowledge synthesis in multi-source, multilingual environments.
Paper Structure (17 sections, 8 equations, 3 figures, 3 tables)

This paper contains 17 sections, 8 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Preliminaries & Related Works
  3. Methodology
  4. Problem Formulation
  5. Entity-Centric Graph Partitioning
  6. Exhaustive Batch Pairing
  7. Linearization and LLM Reasoning
  8. Robust Response Parsing and Resolution
  9. Agglomeration Fusion and Schema Unification
  10. Experiments and Results
  11. Experimental Setup
  12. Quantitative Performance Metrics
  13. Hits@k Analysis and Source Accuracy
  14. Impact of Confidence Filtering
  15. Conclusion
  16. ...and 2 more sections

Figures (3)

  • Figure 1: Conceptual framework for LLM-based cross-lingual knowledge graph fusion. Heterogeneous input graphs in English ($G_{en}$), Chinese ($G_{zh}$), and French ($G_{fr}$) are processed through a fusion framework that linearizes structural triplets into natural language and the LLM acts as a semantic bridge to reconcile entities.
  • Figure 2: Overview of the proposed modular framework for $N$-Graph Knowledge Graph Fusion.
  • Figure 3: Details of the LLM prompting interface. The system prompt (left) defines the operational constraints and confidence thresholds, while the user prompt (right) serves as the data payload, containing the linearized triples from the source and target knowledge graphs.