发表机构
University of Galway（戈尔韦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有基于LLM的知识图谱补全方法的不足，提出结合离散结构编码与相似实体信息的CoSC方法，在FB15k-237数据集上取得更优性能。
AI 中文摘要
知识图谱补全要求模型同时利用文本描述与关系结构。现有基于大语言模型（LLM）的方法要么将知识图谱（KG）结构编码为离散标记，要么对受限候选实体集进行优化，且这两个方向大多被分开研究。我们提出用于基于LLM的知识图谱补全（KGC）的CoSC，它结合离散结构编码与相似实体信息。具体而言，LLM从离散结构编码生成初始候选实体排序，之后利用与查询实体结构相似的实体信息优化该排序。在FB15k-237上的实验表明，CoSC在平均倒数排名（MRR）和Top10命中率（Hits@10）上优于现有基线，同时在Top1命中率（Hits@1）上保持竞争力。
英文摘要
Knowledge graph completion requires models to use both textual descriptions and relational structure. Existing LLM-based methods either encode KG structure as discrete tokens or refine a restricted set of candidate entities, and these two directions have largely been studied separately. We propose CoSC for LLM-based KGC, which combines discrete structural coding with similar entity information. Specifically, an LLM generates an initial candidate entity ranking from discrete structural codes, after which information from entities with structures similar to that of the query entity refines the ranking. Experiments on FB15k-237 show that CoSC outperforms existing baselines on MRR and Hits@10 while remaining competitive on Hits@1.
CommentsAccepted by ISWC 26 Posters and Demos Track
