LLM-Based Knowledge Graph Completion Combining Discrete Structural Coding with Similar Entity Information
2026-08-31 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created a new method called CoSC to improve how large language models (LLMs) predict missing information in knowledge graphs. They combined two approaches: using coded structural information and looking at similar entities to help choose the best answers. Their experiments showed that CoSC works better than previous methods on some accuracy measures while still performing well on others. This means their method helps LLMs understand the connections between things more effectively.
knowledge graph completionlarge language modelsdiscrete structural codingentity rankingFB15k-237mean reciprocal rankhits@10hits@1relational structureentity similarity
Authors
Jiaqi Wang, Dongying Lin, Yang Yang, Yinan Liu, Bin Wang, Xiaochun Yang
Abstract
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.