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:智能技术的一个日益普遍的问题是文本安全,因为不受控制的系统可能会向其用户提出建议,导致伤害或危及生命的后果。然而,生成的可造成身体伤害的语句的清晰度各不相同。在本文中,我们区分可能导致身体伤害的文字类型,并建立一个特别未得到充分探讨的类别:隐蔽的不安全文本。然后,我们进一步分解系统信息方面的这一类别,并讨论减少在每一个子类中生成文字的方法。归根结底,我们的工作界定了造成身体伤害的隐蔽的不安全语言问题,并主张利益攸关方和监管者必须优先处理这一微妙而危险的问题。我们强调缓解战略,以激励未来的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内部的安全。