تقرير
Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models
العنوان: | Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models |
---|---|
المؤلفون: | Lopez-Martinez, Daniel |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Artificial Intelligence |
الوصف: | Generative AI (GenAI) models have demonstrated remarkable capabilities in a wide variety of medical tasks. However, as these models are trained using generalist datasets with very limited human oversight, they can learn uses of medical products that have not been adequately evaluated for safety and efficacy, nor approved by regulatory agencies. Given the scale at which GenAI may reach users, unvetted recommendations pose a public health risk. In this work, we propose an approach to identify potentially harmful product recommendations, and demonstrate it using a recent multimodal large language model. Comment: CVPR 2024 Responsible Generative AI (ReGenAI) workshop |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2406.16455 |
رقم الأكسشن: | edsarx.2406.16455 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |