arXiv:2610.17989v1 Announce Type: cross Abstract: A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view. Continuing this conversation, if a user provid...
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.
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.
A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view. Continuing this conversation, if a user provides a prescription with an opposite direction, medic...
The study identifies a specific attention head (L8H10) in Vision Transformers that reads annotation text on chest X‑ray images instead of lung pathology, affecting 62% of COVID‑19 images. Causal inpainting experiments confirm that the head’s behavior is driven by annotation content, and removing the head increases lung attention by 1.52×. This spurious annotation‑attending behavior is consistent across multiple ViT architectures and datasets, persists after full fine‑tuning, and is invisible to standard output‑level evaluation, highlighting the need for mechanistic auditing.
arXiv:2609.15635v1 Announce Type: cross Abstract: A radiology report can already answer a clinical question, so it is hard to tell whether a vision-language model also uses the image. ModaLens, a pai...
arXiv:2610.00111v1 Announce Type: new Abstract: Model judges now supervise multimodal systems at scale, filtering training data, selecting outputs, and supplying the reward that shapes multimodal rea...
arXiv:2604. 15231v2 Announce Type: replace Abstract: Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (CT).
arXiv:2607. 09349v1 Announce Type: cross Abstract: Retrieval-augmented generation evaluation checks whether model claims are factually grounded in retrieved documents.
The paper investigates when a language‑model judge can truly ground its verdicts in code correctness. It shows that current multi‑agent verification methods rely on evidence that is both independent of the answer and distinct between candidates—conditions that fail in code judging. By analyzing two label‑free measurements from the judge’s logs, the authors demonstrate that gating on one measurement allows the system to decline uncertain comparisons, improving accuracy from 20.7% to 36.9% while still answering half of all cases.
arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply...
arXiv:2610.17576v1 Announce Type: cross Abstract: Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it. A false answer pres...