论文标题
foveate，属性和合理化：迈向身体安全和值得信赖的AI
Foveate, Attribute, and Rationalize: Towards Physically Safe and Trustworthy AI
论文作者
论文摘要
随着智能系统的市场不断增长，用户的身体安全是一个日益关注的问题，不受约束的系统可能会建议用户危险的行动，从而导致严重伤害。秘密不安全的文字是一个特别感兴趣的领域，因为这种文本可能是从日常情况引起的，并且具有挑战性地发现有害。我们提出了一个新颖的框架，这是一个新颖的框架，利用外部知识在安全背景下为可信赖的理由产生。特别是，在缺少知识的情况下，农场有资格在特定情况下推理所需的信息，并以可信赖的来源检索这些信息。这些知识既用于对原始文本的安全性进行分类并产生人类解动的理由，从而向特定用户群体阐明了系统的风险，并帮助两个利益相关者管理其系统和政策制定者的风险，以为消费者安全提供具体的保障措施。我们的实验表明，农场在Safetext数据集上获得了最先进的结果，显示安全分类精度的绝对提高了5.9％。
Users' physical safety is an increasing concern as the market for intelligent systems continues to grow, where unconstrained systems may recommend users dangerous actions that can lead to serious injury. Covertly unsafe text is an area of particular interest, as such text may arise from everyday scenarios and are challenging to detect as harmful. We propose FARM, a novel framework leveraging external knowledge for trustworthy rationale generation in the context of safety. In particular, FARM foveates on missing knowledge to qualify the information required to reason in specific scenarios and retrieves this information with attribution to trustworthy sources. This knowledge is used to both classify the safety of the original text and generate human-interpretable rationales, shedding light on the risk of systems to specific user groups and helping both stakeholders manage the risks of their systems and policymakers to provide concrete safeguards for consumer safety. Our experiments show that FARM obtains state-of-the-art results on the SafeText dataset, showing absolute improvement in safety classification accuracy by 5.9%.
