Related papers: Graph Fusion Across Languages using Large Language Models

Graph Fusion Across Languages using Large Language Models

URL: http://arxiv.org/abs/2603.21248v1
Date: Sun, 22 Mar 2026 14:10:09 GMT
Title: Graph Fusion Across Languages using Large Language Models
Abstract summary: We propose a framework for cross-lingual graph fusion, leveraging the in-context reasoning and multilingual semantic priors of Large Language Models (LLMs)<n>The framework implements structural linearization by mapping triplets directly into natural language sequences.
Score: 1.0609815608017066
License: http://creativecommons.org/licenses/by/4.0/
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.

Related papers

ViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph Completion [13.875849657353292]
We propose ViSR-KGC, a visual subgraph reasoning approach for knowledge graph completion.<n>It integrates three complementary capabilities to capture semantic correlations.<n>Based on learned multimodal embeddings, our framework first extracts a compact and query-aware subgraph.
arXiv Detail & Related papers (2026-08-06T10:01:54Z)
Towards Efficient LLM-aware Heterogeneous Graph Learning [47.42705995672551]
We propose an Efficient LLM-Aware framework for heterogeneous graphs.<n>Our proposed ELLA outperforms state-of-the-art methods in the performance and efficiency.
arXiv Detail & Related papers (2025-11-22T05:38:03Z)
AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries? [31.91169297907121]
AmbiGraph-Eval is a novel benchmark of real-world ambiguous queries paired with expert-verified graph query answers.<n>Our findings reveal a critical gap in ambiguity handling and motivate future work on specialized resolution techniques.
arXiv Detail & Related papers (2025-08-13T09:06:59Z)
POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering [69.52231076699756]
PolyChartQA is the first large-scale multilingual chart question answering benchmark covering 22,606 charts and 26,151 question-answering pairs across 10 diverse languages.<n>We leverage state-of-the-art LLM-based translation and enforce rigorous quality control in the pipeline to ensure the linguistic and semantic consistency of the generated multilingual charts.
arXiv Detail & Related papers (2025-07-16T06:09:02Z)
LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models [87.68057302738457]
Text-Attributed Graphs (TAGs) are ubiquitous in real-world scenarios.<n>Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, existing approaches suffer from decoupled architectures.<n>We propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning.
arXiv Detail & Related papers (2025-03-05T09:45:22Z)
Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text [44.81698187939784]
This paper introduces Structure Guided Prompt, a framework designed to improve the multi-step reasoning capabilities of Large Language Models (LLMs) Our experiments show that this framework significantly enhances the reasoning capabilities of LLMs, enabling them to excel in a broader spectrum of natural language scenarios.
arXiv Detail & Related papers (2024-02-20T22:56:23Z)
Multimodal Graph Learning for Generative Tasks [89.44810441463652]
Multimodal learning combines multiple data modalities, broadening the types and complexity of data our models can utilize. We propose Multimodal Graph Learning (MMGL), a framework for capturing information from multiple multimodal neighbors with relational structures among them.
arXiv Detail & Related papers (2023-10-11T13:25:03Z)
Integrating Graphs with Large Language Models: Methods and Prospects [68.37584693537555]
Large language models (LLMs) have emerged as frontrunners, showcasing unparalleled prowess in diverse applications. Merging the capabilities of LLMs with graph-structured data has been a topic of keen interest. This paper bifurcates such integrations into two predominant categories.
arXiv Detail & Related papers (2023-10-09T07:59:34Z)
Language is All a Graph Needs [33.9836278881785]
We propose InstructGLM (Instruction-finetuned Graph Language Model) with highly scalable prompts based on natural language instructions. Our method surpasses all GNN baselines on ogbn-arxiv, Cora and PubMed datasets.
arXiv Detail & Related papers (2023-08-14T13:41:09Z)
GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction [107.8262586956778]
We introduce graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations. GCNs struggle to model words with long-range dependencies or are not directly connected in the dependency tree. We propose to utilize the self-attention mechanism to learn the dependencies between words with different syntactic distances.
arXiv Detail & Related papers (2020-10-06T20:30:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.