GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41604-41606
DOI: 10.1609/aaai.v40i48.42354 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yujia Hu und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Language models are powerful artifacts, 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. This demo 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 systematic analysis of LLM knowledge, as well as for automated KB construction.
Zitieren
APA
Hu, Y., Nguyen, T., Ghosh, S., Müller, M., & Razniewski, S. (2026). GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41604-41606. https://doi.org/10.1609/aaai.v40i48.42354
Vancouver
Hu Y, Nguyen T, Ghosh S, Müller M, Razniewski S. GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41604-41606. doi:10.1609/aaai.v40i48.42354
BibTeX
@article{Hu2026,
author = {Hu, Yujia and Nguyen, Tuan-Phong and Ghosh, Shrestha and Müller, Moritz and Razniewski, Simon},
title = {GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41604--41606},
doi = {10.1609/aaai.v40i48.42354}
}
EUVIMED