让知识图谱直接用大模型能懂的语言说话，提升复杂推理能力。
The Graph Language: How Knowledge Graphs Speak to Large Language Models
- 用关系型标记将图结构转化为大模型可理解的语义
- 在多跳推理任务上显著超越现有方法
- 适合需要精准知识推理的应用场景
大型语言模型（LLM）在推理方面表现优异，但需知识图谱（KG）提供事实支撑。我们提出GRALAN，通过关系型标记使知识图谱能直接在大模型的语义空间中“说话”，保留图结构。GRALAN-可训练的语言中介器为任意冻结的LLM生成结构化标记，构建知识密集型应用基础。我们将问答任务重构为面向问题子图的实体分类，实验表明其在复杂多跳推理任务中显著优于现有方法，建立了一种保持结构保真度的同时利用大模型推理能力的新范式。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at reasoning but benefit from grounding provided by Knowledge Graphs (KGs). However, integrating these paradigms is challenging. We introduce GRALAN, which enables KGs to speak directly in the LLM's semantic space through relational tokens that preserve graph structure. GRALAN-s trainable language mediator generates structured tokens for any frozen LLM, creating a foundation for knowledge-intensive applications. We demonstrate its effectiveness in question-answering by re-framing the task as entity classification over question-focused subgraphs. Experiments show that GRALAN significantly outperforms existing methods, particularly on complex multi-hop reasoning tasks, establishing a new paradigm for KG-LLM integration that maintains structural fidelity while leveraging LLMs' reasoning capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。