arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.16455cs.AI
收藏

用于避免生成式AI模型中有害医疗产品推荐及超说明书推广的护栏机制

Guardrails for avoiding harmful medical product recommendations and off-label promotion in generative AI models

Amazon(亚马逊公司)

Daniel Lopez-Martinez

AI总结:

针对生成式AI因通用数据集训练可能输出未获批医疗产品推荐的公共健康风险,研究提出识别有害医疗产品推荐的护栏方法,并用多模态大语言模型完成验证。

摘要:

生成式AI(GenAI)模型已在各类医疗任务中展现出卓越能力。但由于这类模型使用人工监督极为有限的通用数据集训练,可能会习得尚未经过充分安全性和有效性评估、也未获监管机构批准的医疗产品用途。考虑到GenAI可能触达的用户规模,未经审核的推荐会构成公共健康风险。本研究提出一种识别潜在有害产品推荐的方法,并借助一款最新的多模态大语言模型验证了该方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑