An increasingly prevalent problem for intelligent technologies is text safety, as uncontrolled systems may generate recommendations to their users that lead to injury or life-threatening consequences. However, the degree of explicitness of a generated statement that can cause physical harm varies. In this paper, we distinguish types of text that can lead to physical harm and establish one particularly underexplored category: covertly unsafe text. Then, we further break down this category with respect to the system's information and discuss solutions to mitigate the generation of text in each of these subcategories. Ultimately, our work defines the problem of covertly unsafe language that causes physical harm and argues that this subtle yet dangerous issue needs to be prioritized by stakeholders and regulators. We highlight mitigation strategies to inspire future researchers to tackle this challenging problem and help improve safety within smart systems.
翻译:智能科技面临的越来越普遍的问题是文本安全,因为不受控制的系统可能为其用户产生建议,其中包含可能导致伤害或危及生命的内容。然而,能够导致身体伤害的陈述的明确程度各不相同。在本文中,我们区分了可能导致身体伤害的文本类型,并建立了一个特别未被充分探索的类型:隐蔽的不安全文本。然后,我们进一步分析了与系统信息相关的这一类别,并讨论了减少生成每个子类别中的文本的解决方案。最终,我们的工作定义了会导致身体危害的隐蔽语言问题,并认为这个微妙而危险的问题需要得到利益相关者和监管机构的优先考虑。我们强调缓解策略,以激发未来研究人员解决这一具有挑战性的问题并帮助改善智能系统的安全性。