MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice. Many rely on synthetic conversations or patient simulators, omit patient-uploaded medical images, or evaluate open-end...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
This research introduces MedRealMM, the first large-scale, real-world multimodal benchmark for Chinese online medical consultations, using authentic patient-doctor interactions with image data. It highlights the critical role of visual information for LLM performance in this domain and reveals that current frontier models, while sometimes matching physicians on positive criteria, still struggle with safety-sensitive error avoidance.
Get the day's AI news in one short email. Free.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.