Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction

ArXi:2605.04221v1 Announce Type: cross Clinical named entity recognition from dental progress notes is challenging because documentation is highly unstructured, domain-specific, and often privacy-sensitive. We developed a locally deployable framework that enables small language models to self-generate, verify, refine, and evaluate entity-specific prompts for extracting multiple clinical entities from dental notes.