Tag
This study evaluates the use of Retrieval-Augmented Generation (RAG) and Named Entity Recognition (NER) to improve automated lay summaries of radiological reports, finding that NER enhances readability and quality, while RAG has variable effects depending on fine-tuning.
A large-scale study of graded health-literacy annotations on 6,323 COVID-19 responses shows that disagreement is driven more by task conceptual difficulty than annotator identity, advocating perspectivist modeling for valid inference.
Lifespan health system used GPT-4 to simplify surgical consent forms from three pages to one page at a 6th grade reading level, improving patient understanding and physician adoption. The initiative, deployed in September 2023, has received positive feedback from both patients and clinicians.