GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
Hu, Yujia, Nguyen, Tuan-Phong, Ghosh, Shrestha, Müller, Moritz, Razniewski, Simon
–arXiv.org Artificial Intelligence
Language models are powerful tools, yet their factual knowledge is still poorly understood, and inaccessible to ad-hoc browsing and scalable statistical analysis. This demonstration introduces GPTKB v1.5, a densely interlinked 100-million-triple knowledge base (KB) built for $14,000 from GPT-4.1, using the GPTKB methodology for massive-recursive LLM knowledge materialization (Hu et al., ACL 2025). The demonstration experience focuses on three use cases: (1) link-traversal-based LLM knowledge exploration, (2) SPARQL-based structured LLM knowledge querying, (3) comparative exploration of the strengths and weaknesses of LLM knowledge. Massive-recursive LLM knowledge materialization is a groundbreaking opportunity both for the research area of systematic analysis of LLM knowledge, as well as for automated KB construction. The GPTKB demonstrator is accessible at https://gptkb.org.
arXiv.org Artificial Intelligence
Jul-9-2025
- Country:
- Europe > Germany
- Saxony (0.14)
- Baden-Württemberg > Tübingen Region
- Tübingen (0.14)
- Europe > Germany
- Genre:
- Research Report (0.64)
- Technology: