The recent developments in the research area highlight a significant shift towards leveraging graph-based methodologies and large language models (LLMs) to enhance information retrieval, recommendation systems, and supply chain transparency. Innovations are particularly focused on improving the explainability, efficiency, and applicability of these systems across various domains, including biomedical literature and emerging economies. The integration of LLMs with graph-based systems is proving to be a powerful approach for automating complex processes, such as graph construction and supply chain analysis, thereby addressing longstanding challenges related to computational costs, information asymmetry, and the need for more sophisticated access paths in digital libraries.

Noteworthy papers include:

• A novel graph-based and explainable method for biomedical paper recommendation, demonstrating significant computational efficiency and user benefit.
• An extension of a graph-based discovery system for the biomedical domain, introducing effective ranking methods and query relaxation paradigms for improved precision and recall.
• A study proposing the use of online content and LLMs to enhance supply chain transparency in emerging economies, validated through a case study on the semiconductor supply chain.
• An automatic graph construction framework based on LLMs for recommendation, showing marked improvements in online advertising metrics and serving a vast user base.