RAD-PHI2: Instruction Tuning PHI-2 for Radiology

arXiv:2403.09725v1 Announce Type: new
Abstract: Small Language Models (SLMs) have shown remarkable performance in general domain language understanding, reasoning and coding tasks, but their capabilities in the medical domain, particularly concerning radiology text, is less explored. In this study, we investigate the application of SLMs for general radiology knowledge specifically question answering related to understanding of symptoms, radiological appearances of findings, differential diagnosis, assessing prognosis, and suggesting treatments w.r.t diseases pertaining to different organ systems. Additionally, we explore the utility …

abstract application arxiv capabilities coding cs.ai cs.cl domain general knowledge language language models language understanding medical performance phi phi-2 question question answering radiology reasoning slms small small language models study tasks text type understanding