KIT | KIT-Bibliothek | Impressum | Datenschutz

Predicting New Research Directions in Materials Science using Large Language Models and Concept Graphs

Marwitz, Thomas; Colsmann, Alexander ORCID iD icon 1; Breitung, Ben ORCID iD icon 2; Brabec, Christoph; Kirchlechner, Christoph 3; Blasco, Eva; Marques, Gabriel Cadilha 2; Hahn, Horst 2; Hirtz, Michael ORCID iD icon 2; Levkin, Pavel A. ORCID iD icon 4; Eggeler, Yolita M. ORCID iD icon 5; Schlöder, Tobias ORCID iD icon 2; Friederich, Pascal ORCID iD icon 2,6
1 Lichttechnisches Institut (LTI), Karlsruher Institut für Technologie (KIT)
2 Institut für Nanotechnologie (INT), Karlsruher Institut für Technologie (KIT)
3 Institut für Angewandte Materialien – Werkstoff- und Grenzflächenmechanik (IAM-MMI), Karlsruher Institut für Technologie (KIT)
4 Institut für Organische Chemie (IOC), Karlsruher Institut für Technologie (KIT)
5 Laboratorium für Elektronenmikroskopie (LEM), Karlsruher Institut für Technologie (KIT)
6 Institut für Theoretische Informatik (ITI), Karlsruher Institut für Technologie (KIT)

Abstract (englisch):

Due to an exponential increase in published research articles, it is impossible for individual scientists to read all publications, even within their own research field. In this work, we investigate the use of large language models (LLMs) for the purpose of extracting the main concepts and semantic information from scientific abstracts in the domain of materials science to find links that were not noticed by humans and thus to suggest inspiring near/mid-term future research directions. We show that LLMs can extract concepts more efficiently than automated keyword extraction methods to build a concept graph as an abstraction of the scientific literature. A machine learning model is trained to predict emerging combinations of concepts, i.e. new research ideas, based on historical data. We demonstrate that integrating semantic concept information leads to an increased prediction performance. The applicability of our model is demonstrated in qualitative interviews with domain experts based on individualized model suggestions. We show that the model can inspire materials scientists in their creative thinking process by predicting innovative combinations of topics that have not yet been investigated.


Volltext §
DOI: 10.5445/IR/1000187787
Veröffentlicht am 01.12.2025
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Nanotechnologie (INT)
Institut für Organische Chemie (IOC)
Institut für Theoretische Informatik (ITI)
Laboratorium für Elektronenmikroskopie (LEM)
Lichttechnisches Institut (LTI)
Institut für Angewandte Materialien – Werkstoff- und Grenzflächenmechanik (IAM-MMI)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2025
Sprache Englisch
Identifikator KITopen-ID: 1000187787
HGF-Programm 43.31.01 (POF IV, LK 01) Multifunctionality Molecular Design & Material Architecture
Verlag arxiv
Schlagwörter Machine Learning (cs.LG)
Nachgewiesen in OpenAlex
Dimensions
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page