SKG-LLM: Developing a Mathematical Model for Stroke Knowledge Graph Construction Using Large Language Models
This addresses the problem of organizing complex biomedical literature for stroke researchers, but it is incremental as it applies existing LLM methods to a specific domain.
The study tackled constructing a knowledge graph for stroke research using large language models, achieving a precision of 0.923 and recall of 0.918 with GPT-4 and expert reviews.
The purpose of this study is to introduce SKG-LLM. A knowledge graph (KG) is constructed from stroke-related articles using mathematical and large language models (LLMs). SKG-LLM extracts and organizes complex relationships from the biomedical literature, using it to increase the accuracy and depth of KG in stroke research. In the proposed method, GPT-4 was used for data pre-processing, and the extraction of embeddings was also done by GPT-4 in the whole KG construction process. The performance of the proposed model was tested with two evaluation criteria: Precision and Recall. For further validation of the proposed model, GPT-4 was used. Compared with Wikidata and WN18RR, the proposed KG-LLM approach performs better, especially in precision and recall. By including GPT-4 in the preprocessing process, the SKG-LLM model achieved a precision score of 0.906 and a recall score of 0.923. Expert reviews further improved the results and increased precision to 0.923 and recall to 0.918. The knowledge graph constructed by SKG-LLM contains 2692 nodes and 5012 edges, which are 13 distinct types of nodes and 24 types of edges.