Guest Editor(s)
Prof. Ke Qin
Email: qinke@uestc.edu.cn
Affiliation: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
Homepage:
Research Interests: machine reasoning in LLM, knowledge graph, data mining
Assoc. Prof. Zongyi Xu
Email: xuzy@cqupt.edu.cn
Affiliation: SChool of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China
Homepage:
Research Interests: 3D vision, point cloud registration, human body modelling
Dr. Rui Yang
Email: yangrui66@cdut.edu.cn
Affiliation: College of Computer Science and Cyber Security, Chengdu University of Technology, Chengdu, China
Homepage:
Research Interests: deep learning image processing and AI algorithms for geoscience applications
Summary
With the rapid advancement of large language models (LLMs), their powerful natural language understanding and generation capabilities have revolutionized various artificial intelligence fields, while knowledge graphs (KGs) excel in structured knowledge representation and logical reasoning. The integration of LLMs and KGs has become a frontier research direction, as it can make up for the deficiencies of LLMs in factual accuracy and logical rigor, and enhance the interpretability and practicality of KGs. This research area is of great significance for promoting the innovation of intelligent systems and expanding the application boundaries of AI in emerging scenarios.
This Special Issue aims to gather cutting-edge research on the integration of LLMs and KGs, focusing on integration theories, innovative methods, and practical applications in emerging topics. It covers theoretical exploration of LLM-KG integration, method optimization, and application practices in emerging fields, to promote academic exchanges and technological progress, and provide a platform for researchers to present their latest achievements.
Suggested Themes, but NOT limited to:
1. Theoretical frameworks for the integration of LLMs and knowledge graphs, including cross-modal alignment and knowledge fusion mechanisms.
2. Innovative integration methods of LLMs and KGs, such as prompt engineering-based knowledge injection and KG-enhanced LLM reasoning.
3. Applications of LLM-KG integration in emerging fields of intelligent healthcare, such as medical knowledge reasoning and clinical decision support.
4. Application of LLM-KG integration in industrial digital transformation, such as intelligent scheduling and supply chain risk prediction.
5. Lightweight integration methods of LLMs and KGs for edge computing and Internet of Things (IoT) scenarios.
6. Evaluation metrics and experimental validation for LLM-KG integration systems in emerging application topics.
Keywords
Large language models (LLMs), knowledge graphs (KGs), machine reasoning, multimodal data processing.
Login
Register
Submit a Paper
Propose a Special lssue