Improving Translational Accuracy
Improving Translational Accuracy
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Jun 29, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Jack Lott1, Brett Stubbert2, David McShannon3
1School of Medicine, Queen's University, 80 Barrie Street, Kingston, ON K7L 3N6, Canada.
Chain-of-Verification (CoVe) prompting significantly enhances the extraction of National Institutes of Health Stroke Scale (NIHSS) data by smaller large language models (LLMs). While performance in larger models remains unchanged, CoVe shows promise for improving automated stroke care documentation.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: