CoSC is proposed, which combines discrete structural coding with similar entity information to generate 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.
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.
These results demonstrate that collaborative modeling of instance-level and batch-level structural context can effectively enhance structure-aware entity representation and improve fine-grained entity prediction.
An LLMs-augmented knowledge graph (LAKG) model for semantic-aware recommendation is proposed, which introduces LLMs to extract semantic features from associated texts to enhance the semantic-aware ability.
Yuan-Ming Zhang, Yongbiao Lou, Wen-Bo Zheng et al.· ACM Transactions on Knowledg...· 0 citations
A novel unsupervised entity alignment framework, named LLM‐Align, is presented to effectively leverage Large Language Models to precisely annotate entity pairs, which alleviates structural heterogeneity between aligned entities.
Zhi-Huan Yan, Yi Wang, Chong-Chong Zhang et al.· Expert systems· 0 citations
PEARL is proposed, a Path-Entity Aligned Relational Learning framework that models paths as context-conditioned reasoning signals and employs a dual-view contrastive objective that promotes representation consistency under stochastic contextual perturbations.
Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activa...
A novel multimodal entity alignment model- TextFusionEA is proposed, which implements structural embedding based on GraphSAGE, uses MobileNetV3 to obtain visual features, introduces an adaptive fusion mechanism of semantic, structural, and visual features, and designs a semi supervised iterative learning strategy to ex...
