Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning
This work addresses inefficiencies and performance gaps in using large language models for knowledge graph completion, offering a domain-specific improvement for AI applications in structured data reasoning.
The paper tackles the problem of knowledge graph completion (KGC) by addressing inconsistent representation spaces between natural language and graph structures, and the inefficiency of separate instructions for different tasks, proposing a structure-aware alignment-tuning framework that improves link prediction by 8.7% to 29.8% over state-of-the-art methods.
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%.