Quelltext der Seite Techreport3054

{{Publikation Erster Autor
|ErsterAutorVorname=Yujia
|ErsterAutorNachname=Hu
|FurtherAuthors=Tuan-Phong Nguyen; Shrestha Ghosh; Simon Razniewski
}}
{{Techreport
|Title=GPTKB: Comprehensively Materializing Factual LLM Knowledge
|Year=2024
|Month=November
|Institution=arXiv.org
}}
{{Publikation Details
|Abstract=LLMs have majorly advanced NLP and AI, and next to their ability to perform a wide range of procedural tasks, a major success factor is their internalized factual knowledge. Since (Petroni et al., 2019), analyzing this knowledge has gained attention. However, most approaches investigate one question at a time via modest-sized pre-defined samples, introducing an availability bias (Tversky and Kahnemann, 1973) that prevents the discovery of knowledge (or beliefs) of LLMs beyond the experimenter's predisposition.
To address this challenge, we propose a novel methodology to comprehensively materializing an LLM's factual knowledge through recursive querying and result consolidation.
As a prototype, we employ GPT-4o-mini to construct GPTKB, a large-scale knowledge base (KB) comprising 105 million triples for over 2.9 million entities - achieved at 1% of the cost of previous KB projects. This work marks a milestone in two areas: For LLM research, for the first time, it provides constructive insights into the scope and structure of LLMs' knowledge (or beliefs). For KB construction, it pioneers new pathways for the long-standing challenge of general-domain KB construction. GPTKB is accessible at this https://gptkb.org
|Link=https://arxiv.org/abs/2411.04920
|Forschungsgruppe=Knowledge-aware Artificial Intelligence
}}