On Monday, April 28th, at 15:00, CEDAR will host Prof. Simon Razniewski from TU Dresden.
We invite you to join us for the talk of Prof. Razniewski, titled:
“GPTKB: Comprehensively Materializing Factual LLM Knowledge”
The talk will take place at the Henri Poincaré room (RDC, Alan Turing building).
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 101 million triples for over 2.9 million entities – achieved at 1% of the cost of previous KB projects. This contributes to two discourses: 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.
Presentation slides are availble here
Bio:
Simon Razniewski is a professor of knowledge-aware AI at ScaDS.AI Dresden/Leipzig and TU Dresden, where he develops novel methods for extracting and consolidating knowledge from and with language models and knowledge bases. Simon Razniewski was previously a research scientist at the Bosch Center for AI (2023-2024), senior researcher at the Max Planck Institute for Informatics (2017-2021), where he was heading the Knowledge Base Construction and Quality area, and assistant professor at the Free University of Bozen Bolzano (2014-2017). He holds a PhD from the Free University of Bozen-Bolzano (2014), and a Diploma (MSc.) from TUD Dresden University of Technology (2010). Simon Razniewski has published more than 20 papers at premier conferences in the area of artificial intelligence.
