{"ID":2896927,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.05740","arxiv_id":"2507.05740","title":"GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge","abstract":"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.","short_abstract":"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 method...","url_abs":"https://arxiv.org/abs/2507.05740","url_pdf":"https://arxiv.org/pdf/2507.05740v1","authors":"[\"Yujia Hu\",\"Tuan-Phong Nguyen\",\"Shrestha Ghosh\",\"Moritz Müller\",\"Simon Razniewski\"]","published":"2025-07-08T07:37:12Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","project_urls":"[\"https://gptkb.org\"]","has_code":false}