Saved in:
Bibliographic Details
Main Authors: Hu, Yujia, Nguyen, Tuan-Phong, Ghosh, Shrestha, Müller, Moritz, Razniewski, Simon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05740
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912472030511104
author Hu, Yujia
Nguyen, Tuan-Phong
Ghosh, Shrestha
Müller, Moritz
Razniewski, Simon
author_facet Hu, Yujia
Nguyen, Tuan-Phong
Ghosh, Shrestha
Müller, Moritz
Razniewski, Simon
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05740
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
Hu, Yujia
Nguyen, Tuan-Phong
Ghosh, Shrestha
Müller, Moritz
Razniewski, Simon
Computation and Language
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.
title GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
topic Computation and Language
url https://arxiv.org/abs/2507.05740