Bio: Cogan Shimizu is an Assistant Professor at Wright State University in Dayton, Ohio, USA and is the director of the Knowledge and Semantic Technologies Laboratory. His work focuses on the construction of knowledge graphs and ontologies, especially with pattern-based methods, using both human-driven and AI-assisted methodologies. Other interests include knowledge engineering, broadly defined, from the use of knowledge representation (symbolic AI) into neural systems (e.g., Neurosymbolic AI) to the formulation of ontological understanding of domain science. His work has been published in the journal of web semantics, the semantic web journal, and various highly prominent Semantic Web conferences. Currently, he leads the Education Gateway to the Proto-OKN, which focuses on the development of educational material for knowledge graphs.

Abstract: Large Language Models bear the promise of significant acceleration of key Knowledge Graph and Ontology Engineering tasks, including ontology modeling, extension, modification, population, alignment, as well as entity disambiguation. We lay out LLM-based Knowledge Graph and Ontology Engineering as a new and coming area of research, and argue that modular approaches to ontologies will be of central importance.

Bio: Jennifer D’Souza is a senior postdoctoral researcher at the TIB Leibniz Information Centre for Science and Technology, where her expertise in AI, NLP, and scientific knowledge extraction drives her research. At TIB, Jennifer leads the NLP-AI aspect of the Open Research Knowledge Graph (ORKG) project and heads the SCINEXT project, aimed at advancing neuro-symbolic AI and NLP methods for scholarly innovation extraction, supported by the German Federal Ministry of Education and Research.

Abstract: In this talk, I will present our recent research in evaluating large language models (LLMs) for both structured and unstructured scientific summarization. Drawing from collaborative studies across the Open Research Knowledge Graph and scientific question answering benchmarks, my talk aims to highlight how LLMs can aid scalable, semantically rich synthesis while also addressing challenges in alignment, robustness, and evaluation reliability.