Healthcare and education systems increasingly rely on complex, knowledge-intensive web platforms generating large-scale heterogeneous data. While Large Language Models excel at natural language understanding and human-computer interaction, directly applying general-purpose LLMs to these domains faces significant challenges including factual accuracy, lack of domain knowledge representation, and insufficient interpretability needed for sensitive applications.
Knowledge-enhanced LLMs address these limitations by incorporating structured knowledge, Web semantics, and multimodal representations into language models. This approach improves reliability, explainability, and controllability while enabling better integration with existing system components such as data retrieval and information management modules. The special issue seeks high-quality research on theoretical models, methods, frameworks, and applications of knowledge-enhanced LLMs specifically designed for healthcare and education web services.