In the KnowledgeHub (KH) project, we exploit knowledge coming from many different sources (structured and unstructured) to address some current LLM limitations. Specifically, we envision KH as a symbiotic system that aims to couple knowledge represented in LLMs with structured data in knowledge graphs and relational databases as well as unstructured data in text corpora.
In the KnowledgeHub, the repository is expanded in a continuous and (semi-)automated paradigm with data from a variety of sources and types. Our focus is human resources (HR); as such, we incorporate text corpora such as:
- Structured Data: Information from knowledge graphs, relational databases, and other structured sources.
- Unstructured Data: Text corpora, such as resumes, job descriptions.
- Taxonomy Data: taxonomies of skills, titles, and other HR concepts.
Information ingested from these sources is captured in a variety of representations, including symbolic (as property graphs, for example) as well as dense numerical representations (such as embeddings or models) and hybrid mixtures of those.
We believe the hybrid and symbiotic learning approach, in KnowledgeHub, can deliver artifacts that capture context effectively, provide controllable, consistent and interpretable outputs, and improve fairnes of decision-making.