Knowledge Graphs and Large Language Models

Current Approaches, Challenges, and Future Directions
Erscheinungsjahr 2026
ISBN: 978-0-443-45244-4
Verlag: Elsevier Science

Buch, Englisch, 320 Seiten, Format (B × H): 191 mm x 235 mm, Gewicht: 449 g

Knowledge Graphs and Large Language Models: Current Approaches, Challenges, and Future Directions explores the cutting-edge fusion of two powerful artificial intelligence technologies: Large Language Models (LLMs) and Knowledge Graphs (KGs). The book is structured to provide a comprehensive understanding of this emerging field. Chapters introduce the synergy between LLMs and KGs, delve into the capabilities and challenges of LLMs, focus on the structure, function, and significance of KGs, present a conceptual framework for bridging LLMs and KGs, discuss techniques for their integration, explore how LLMs can enhance KGs and vice versa, and showcase applications of LLM-KG synergy across various domains.

Final sections addresses ethical, social, and technical challenges and future innovations. The book concludes by summarizing key insights and advancements in intelligent systems. This is an essential resource for graduate students, researchers, and professionals in computer science. It offers valuable insights for adopting LLMs, KGs, and their advanced applications in research and product development. By bridging the gap between these technologies, this book equips readers with the knowledge to drive innovation and enhance the capabilities of intelligent systems.

Autoren/Hrsg.

Groppe, Sven

Groppe, Jinghua

Mihindukulasooriya, Nandana

Fachgebiete

• Mathematik | Informatik EDV | Informatik Business Application Unternehmenssoftware
• Wirtschaftswissenschaften Betriebswirtschaft Betriebswirtschaft: Theorie & Allgemeines

Inhaltsverzeichnis

1. Introduction. Understanding the Synergy Between LLMs and KGs
2. Foundations of Large Language Models. Capabilities and Challenges
3. Knowledge Graphs. Structure, Function, and Significance
4. Bridging LLMs and KGs. A Conceptual Framework
5. Techniques for Integrating LLMs and KGs
6. Enhancing Knowledge Graphs With Large Language Models
7. Improving Language Models With Knowledge Graph Insights
8. Applications of LLM–KG Synergy Across Domains
9. Ethical, Social, and Technical Challenges in LLM–KG Integration
10. GOSt-MT. A Knowledge Graph for Occupation-Related Gender Biases in Machine Translation
11. Future Innovations in Combining LLMs and KGs
12. Conclusion. Advancing the Frontiers of Intelligent Systems

Über Autor(innen)

Groppe, Jinghua
Jinghua Groppe is a postdoctoral fellow at the University of Lübeck, Germany. She has been involved in a large number of research projects in Artificial Intelligence, Quantum Computing, Semantic Web, Information Technology and other areas of Computer Science. She has extensive research experience and has published over sixty papers in peer-reviewed journals, conferences and workshops. She serves as a reviewer for the German Research Foundation (DFG) and for a large number of journals and conferences, and also co-organizes conferences, workshops and special issues for journals Her current research areas include generative AI, LLMs, graph neural networks, knowledge graphs, quantum computing, and the application of artificial intelligence in cybersecurity and in the automation of business processes. In addition to her research projects, she also works with industry on technology transfer projects and applies AI to automated business processes.

Mihindukulasooriya, Nandana
Nandana Mihindukulasooriya is a Senior Research Scientist at IBM Research, New York, USA. He holds a PhD in Artificial Intelligence from Universidad Politecnica de Madrid, Spain. His research interests include knowledge graphs, knowledge representation and reasoning, Semantic Web, Linked Data, and generative AI. Nandana has published more than 85 peer-reviewed papers in prestigious journals and conferences on Semantic Web and Knowledge Graph related topics with an h-index of 21. He has contributed as a PC member to several conferences, including WWW, AAAI, ACL, EMNLP, IJCAI, ISWC, ESWC, SAC, and K-CAP, among others. Nandana has previously co-organized several workshops, including NLP4KGC 2023-2024 @ WWW/ TheWebConf and SEMANTiCS, Text2KG 2022-2024 at Extended Semantic Web Conference (ESWC), SMART 2020-2022, ScholarlyQALD 2023, KGSum 2022 at International Semantic Web Conference (ISWC), ToursimKG 2018 @ ICWE. In addition, Nandana has been the general chair, publicity chair, and sponsorship chair of IHIC 2022, ISIC 2023, and ISWC 2024.

Groppe, Sven
Sven Groppe is a Professor at the University of Lübeck, Germany. He was the project leader of the DFG project LUPOSDATE with a focus on Semantic Web Database techniques and was the project leader of two research projects on FPGA acceleration of relational and Semantic Web databases. He is the project coordinator of the BMBF-funded QC4DB project about database optimizations accelerated by quantum computing. Furthermore, he is the principal investigator of three DFG projects, one dealing with GPU acceleration of database indices, one in the area of Semantic Internet of Things and one about high-quality COVID-19 knowledge graphs. Over 100 program committee memberships in international conferences and workshops, reviewer activities in over 40 internationally recognized journals, editorship in 4 journals and chairing of Semantic Big Data, Big Data in Emergent Distributed Environments, Very Large Internet of Things and Quantum Data Science and Management workshops at the world-class ACM SIGMOD and VLDB conferences, and General Chair of the International Semantic Intelligence Conference, International Conference on Applied Machine Learning and Data Analytics and International Healthcare Informatics Conference as well as co-authorship with 191 scientists from 28 countries on 6 continents demonstrate a strong integration into the scientific community of Sven Groppe.