GPTKB: Comprehensively Materializing Factual LLM Knowledge
From International Center for Computational Logic
GPTKB: Comprehensively Materializing Factual LLM Knowledge
Talk by Simon Razniewski
- Location: APB 3027
- Start: 9. January 2025 at 11:00 am
- End: 9. January 2025 at 12:00 pm
- Research group: Knowledge-aware Artificial Intelligence
- Event series: Research Seminar Logic and AI
- iCal
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 materialize 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 potentially marks a milestone in two areas: (1) 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 https://gptkb.org.
