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.

翻译：跨语言知识图谱的融合因语义异构和图环境的复杂性而长期面临挑战。本文提出了一种跨语言图融合框架，利用大语言模型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，使大语言模型能够在动态融合图（$G_{c}^{(t-1)}$）与新候选图（$G_{t}$）之间进行关系映射和实体对齐。基于DBP15K数据集的探索性研究表明，大语言模型可作为通用语义桥梁解决跨语言歧义问题。实验结果显示，该框架成功实现了多个异构图的顺序聚合，为多源多语言环境下的持续知识融合提供了可扩展、模块化的解决方案。