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.
Abstract (translated)
跨语言知识图谱（KGs）的融合因语义异构性和图结构的复杂性而长期面临挑战。本研究提出一种跨语言图融合框架，利用大语言模型（LLMs）的上下文推理能力与多语言语义先验知识。该框架通过将三元组直接映射为自然语言序列（如[头实体][关系][尾实体]）实现结构线性化，使LLM能够在演化融合图（$G_{c}^{(t-1)}$）与候选新图（$G_{t}$）之间映射关系并调和实体。在DBP15K数据集上的探索性研究表明，LLMs可作为通用语义桥梁解决跨语言差异。实验结果显示多个异构图成功实现顺序聚合，为多源多语言环境下的持续知识整合提供了可扩展、模块化的解决方案。
URL
https://arxiv.org/abs/2603.21248
