Trick-or-Treat is an adversarial multimodal medical benchmark that pairs real chest radiographs with synthetic clinical photographs to test cross‑modal reasoning. Each condition has matched pairs where the radiograph and photograph suggest the same disease, and mismatched pairs where the photograph shows an alternative finding. In tests of three frontier models, hallucinations of clinically significant findings rose from 25‑37.5% for single photographs to 45‑57.5% when mismatched pairs were presented, with models often ignoring mismatches and generating findings that better aligned with the radiograph.
arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.
arXiv:2511.22232v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly capable in medical imaging, yet most focus on single-image settings. Clinical inter...
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 paper introduces MedQA-MM, a benchmark that exposes shortcut reasoning in medical multimodal multiple-choice questions. By auditing prompts, images, and modalities, the authors show that models often rely on textual cues rather than visual evidence, with full-input accuracy at 62.63% but only 5.21% when restricted to text. The study highlights the need for route-level evidence to validate true medical image reasoning.
arXiv:2606. 28556v1 Announce Type: new Abstract: Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging.
arXiv:2608.22323v1 Announce Type: new Abstract: The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus...
arXiv:2607. 25933v1 Announce Type: cross Abstract: Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practice, including progressive disclosure of multimodal information, dynamic updating of diagnostic hypotheses, and continuous refinement of clinical reasoning.
arXiv:2610.06896v1 Announce Type: new Abstract: Frontier multimodal large language models (MLLMs) are increasingly positioned as general purpose visual reasoners as part of the quest for artificial g...
With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation.
arXiv:2605. 22547v3 Announce Type: replace-cross Abstract: Medical image diagnosis has achieved significant progress with deep learning, yet existing methods often rely on isolated visual evidence and lack the ability to effectively leverage similar cases and external knowledge.
arXiv:2609.14124v1 Announce Type: cross Abstract: Medical image analysis is often hindered by biased datasets, which can lead to biased models and limited clinical applicability. A promising strategy...
arXiv:2606. 06407v1 Announce Type: cross Abstract: Medical imaging artificial intelligence has achieved strong performance in isolated image interpretation, but remains poorly aligned with radiological practice, where diagnosis and follow-up rely on comparison across prior studies and analogous reference cases.