Augmenting Knowledge Graph Hierarchies Using Neural Transformers

arXiv:2404.08020v1 Announce Type: cross
Abstract: Knowledge graphs are useful tools to organize, recommend and sort data. Hierarchies in knowledge graphs provide significant benefit in improving understanding and compartmentalization of the data within a knowledge graph. This work leverages large language models to generate and augment hierarchies in an existing knowledge graph. For small (<100,000 node) domain-specific KGs, we find that a combination of few-shot prompting with one-shot generation works well, while larger KG may require cyclical generation. We present techniques …

abstract arxiv benefit cs.ai cs.cl cs.dl cs.ir cs.lg data generate graph graphs improving knowledge knowledge graph knowledge graphs language language models large language large language models organize small tools transformers type understanding work