SOURCE-LINKED INTELLIGENCE

Corpus Characterization and Inverse Constitutional Fine-Tuning for Style-Aware Radiology Reports

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Automated radiology report generation has advanced rapidly in diagnostic accuracy, yet generated reports frequently diverge from the stylistic conventions of authentic radiologist writing in structure, diction, and uncertainty language, a gap which has direct implications for clinician trust and user experience. To address this, we characterize stylistic variation across 2,000 reports from the CheXpert Plus dataset using Bio-ClinicalBERT embeddings, UMAP dimensionality reduction, and HDBSCAN clustering, identifying five distinct reporting patterns differing in pathology focus, narrative struct

Read original source ↗ Open in workspace

recordType

paper

region

Global