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 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. Our implementation and experimental framework are publicly available in our repository: https://github.com/IC2-Lab-KMUTT/Multilingual-Graph-Fusion
Anthology ID:
2026.kallm-1.11
Volume:
Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Gilles Sérasset, Katerina Gkirtzou, Michael Cochez, Jan-Christoph Kalo
Venues:
KaLLM | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
102–109
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-kgllm-11
DOI:
10.63317/3eka5ehdb339
Bibkey:
Cite (ACL):
Kaung Myat Kyaw, Khush Agarwal, and Jonathan Chan. 2026. Graph Fusion across Languages Using Large Language Models. In Proceedings of the Knowledge Graphs and Large Language Models Workshop (KG-LLM) @ LREC26, pages 102–109, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Graph Fusion across Languages Using Large Language Models (Kyaw et al., KaLLM 2026)
Copy Citation: