Knowledge-enhanced Large Language Models for Web Information Systems in Health and Education

Introduction

With the continued advancement of digitalization in the healthcare and education sectors, the data types, service objects, and application tasks carried by Web information systems are becoming increasingly complex. Online medical platforms, educational resource platforms, and multimodal interactive environments are continuously generating large-scale, heterogeneous, and knowledge-intensive data, requiring systems to possess semantic understanding, knowledge organization, and intelligent interaction capabilities in addition to basic functions such as information storage, data access, and resource management. In recent years, Large Language Models (LLMs) have developed rapidly, demonstrating strong capabilities in tasks such as natural language understanding, question answering, content generation, and human-computer interaction, providing new technological pathways for Web information systems in the healthcare and education sectors to handle complex knowledge resources, support personalized services, and achieve intelligent interaction.

However, directly applying general-purpose LLMs to Web information systems in healthcare and education still faces several challenges. First, the generation process of LLMs primarily relies on parametric knowledge and contextual relationships, lacking explicit representations of domain knowledge boundaries, professional semantic relationships, and task constraints. Therefore, when handling tasks such as medical knowledge and personalized services, it is prone to problems such as factual bias or inconsistent results. Second, medical and educational applications typically require systems with high interpretability and traceability, while the reasoning process of general LLMs is highly implicit, making it difficult to clearly present the relationship between the generated results and domain knowledge and service goals. Furthermore, the data resources upon which network information systems rely often have characteristics such as dynamic updates and multimodal representation, placing higher demands on knowledge integration, semantic alignment, and security management. Therefore, relying solely on the language understanding and generation capabilities of general-purpose LLMs is insufficient to support the reliability, explainability, and controllability required by Web information systems in healthcare and education.

Knowledge-enhanced LLMs provide an important research direction for addressing the above challenges. By incorporating structured knowledge, Web semantics, and multimodal knowledge representation into LLMs, it becomes possible to introduce more explicit domain constraints and semantic associations into generation and reasoning processes, thereby improving the task adaptability of LLMs to professional knowledge and enhancing the explainability of their outputs. Furthermore, knowledge-enhancement mechanisms facilitate the coordinated operation of LLMs with functional modules in Web information systems, such as data integration, information retrieval, and application management, providing more reliable technical support for tasks including medical information services, health question answering, and learning analytics. Against this background, this special issue focuses on knowledge-enhanced LLMs for Web information systems in healthcare and education, and solicits high-quality research contributions on theoretical models, key methods, system frameworks, evaluation mechanisms, and practical applications. It particularly welcomes studies that investigate how knowledge-driven artificial intelligence technologies improve the reliability, explainability, and adaptability of Web-based healthcare and education services, while promoting interdisciplinary advances in generative artificial intelligence, AI agents, multimodal artificial intelligence, and privacy-preserving artificial intelligence.

List of Topic Areas

• Knowledge-enhanced LLM architectures for Web information systems.
• Knowledge graphs, ontologies, and Web semantics for LLM reasoning and generation.
• Retrieval-augmented generation for Web-based health and education services.
• Web knowledge mining, information extraction, and knowledge integration for LLM-based systems.
• Multimodal knowledge representation and fusion for health and learning applications on the Web.
• Trustworthy, explainable, and privacy-preserving LLMs for sensitive Web environments.
• LLM-enhanced medical information retrieval, health question answering, and decision support.
• LLM-enhanced personalized learning, intelligent tutoring, automated assessment, and learning feedback.
• Agentic LLMs and AI agents for Web-based health and education service management.
• Benchmarks, datasets, evaluation metrics, and real-world applications of knowledge-enhanced LLMs in Web information systems.

Submission Information

Submissions of full manuscripts are made using ScholarOne Manuscripts. Registration and access are available here:

Submit via ScholarOne

Author guidelines must be strictly followed. Please see:

Author guidelines

Authors should select (from the drop-down menu) the special issue title at the appropriate step in the submission process, i.e. in response to “Please select the issue you are submitting to”.

Submitted articles must not have been previously published, nor should they be under consideration for publication anywhere else, while under review for this journal.

Abstract Submissions

Abstracts should be emailed to the lead Guest Editor, Weimin Li, at [email protected]. 

Key Dates

Closing date for abstractsubmissions: 1 October 2026

Closing date for manuscript submissions: 1 November 2026