The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2606. 17710v1 Announce Type: cross Abstract: Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image.
The study examines how differences in radiologists’ reporting styles—such as terminology, shorthand, formatting, and detail—affect the evaluation of AI-generated chest X‑ray reports. By quantifying the sensitivity of common metrics to these variations, the authors show that changes in reference reports can shift model rankings. They introduce a taxonomy of reporting variations and a rewriting method, ReRef, that preserves clinical meaning while altering style, and release a validated dataset of paired reference reports to aid future research.
arXiv:2609.27607v1 Announce Type: cross Abstract: An AI-generated radiology report can resemble a physician's report while omitting an abnormality, adding an unsupported finding, or reversing its pre...
arXiv:2607. 25589v1 Announce Type: cross Abstract: Medical-imaging AI benchmarks combine datasets, DICOM rendering, prompts, provider APIs, automated labels, statistical code, manuscripts, and repository releases.
The paper evaluates large language model (LLM) judges for radiology report assessment across multiple imaging modalities and anatomical regions, comparing four existing metrics (RadFact, GREEN, FineRadScore, CRIMSON) with a new metric called VERT. GREEN emerges as the most robust among current metrics, while VERT improves correlation with radiologist judgments by up to 26% over GREEN. The study also shows that ensembling and lightweight fine‑tuning of the Qwen3‑30B model can yield additional performance gains and significant latency reductions.
arXiv:2608. 07550v1 Announce Type: cross Abstract: Vision-language models return structured chest-radiograph findings through interfaces exposing no confidence score, so a receiving institution cannot read off how far to trust an individual judgment.