AI RESEARCH
Selective Fine-Tuning of GPT Architectures for Parameter-Efficient Clinical Text Classification
arXiv CS.CL
•
ArXi:2603.14183v1 Announce Type: new The rapid expansion of electronic health record (EHR) systems has generated large volumes of unstructured clinical narratives that contain valuable information for disease identification, patient cohort discovery, and clinical decision. Extracting structured knowledge from these free-text documents remains challenging because clinical language is highly specialized, labeled datasets are limited, and full fine-tuning of large pretrained language models can require substantial computational resources.