让大模型更懂知识图谱结构，提升推理准确率。
Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning
- 通过多任务对比学习对齐图谱与语言表示空间。
- 统一指令+轻量适配器，在4个数据集上提升8.7%~29.8%。
- 解决跨模态表示不一致和任务指令重复问题，适合图谱推理研究者。
知识图谱补全（KGC）旨在从知识图谱中推断新知识并进行预测。近期大型语言模型（LLM）展现出强大的推理能力。现有LLM增强型KGC方法主要聚焦于设计特定任务指令，取得显著进展。然而仍存在两大挑战：一是忽略自然语言与图结构间表示空间的不一致性；二是多数方法为不同任务设计独立指令，导致重复工作且耗时。为此，我们提出SAT框架，通过结构感知对齐调优增强LLM在KGC中的表现。首先引入层次化知识对齐，利用多任务对比学习将图嵌入与自然语言空间对齐；其次提出结构化指令调优，使用统一图指令结合轻量级知识适配器，引导LLM进行结构感知推理。在四个基准数据集上的两个KGC任务实验表明，SAT显著优于现有最先进方法，尤其在链接预测任务中提升幅度达8.7%至29.8%。
原文摘要 · Abstract (English)
Knowledge graph completion (KGC) aims to infer new knowledge and make predictions from knowledge graphs. Recently, large language models (LLMs) have exhibited remarkable reasoning capabilities. LLM-enhanced KGC methods primarily focus on designing task-specific instructions, achieving promising advancements. However, there are still two critical challenges. First, existing methods often ignore the inconsistent representation spaces between natural language and graph structures. Second, most approaches design separate instructions for different KGC tasks, leading to duplicate works and time-consuming processes. To address these challenges, we propose SAT, a novel framework that enhances LLMs for KGC via structure-aware alignment-tuning. Specifically, we first introduce hierarchical knowledge alignment to align graph embeddings with the natural language space through multi-task contrastive learning. Then, we propose structural instruction tuning to guide LLMs in performing structure-aware reasoning over KGs, using a unified graph instruction combined with a lightweight knowledge adapter. Experimental results on two KGC tasks across four benchmark datasets demonstrate that SAT significantly outperforms state-of-the-art methods, especially in the link prediction task with improvements ranging from 8.7% to 29.8%.
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。