用概念验证层提升分类安全，不确定时交给人类判断。
Classification with Conceptual Safeguards
- 先预测中间概念再决定目标类别，加一层安全验证
- 在保证安全的前提下，通过人类确认提升预测覆盖范围
- 可标记关键概念供人工审查，适合高风险场景使用
我们提出一种新的分类安全方法——概念防护机制（conceptual safeguard），该机制作为模型的验证层，在预测目标结果前先判断中间概念是否存在。通过此架构，防护机制可在不确定时拒绝预测，确保最低准确率。与传统选择性分类器不同，该方法允许人类对拒判样本中的不确定概念进行确认，从而提升整体覆盖范围。我们提出了传播概念预测不确定性的方法，并设计了识别重要概念以供人工审查的策略。在多个真实世界与合成数据集上的实验表明，该方法能在不牺牲安全性的前提下有效提升深度学习任务的性能与覆盖率。
原文摘要 · Abstract (English)
We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the presence of intermediate concepts. Given this architecture, a safeguard ensures that a model meets a minimal level of accuracy by abstaining from uncertain predictions. In contrast to a standard selective classifier, a safeguard provides an avenue to improve coverage by allowing a human to confirm the presence of uncertain concepts on instances on which it abstains. We develop methods to build safeguards that maximize coverage without compromising safety, namely techniques to propagate the uncertainty in concept predictions and to flag salient concepts for human review. We benchmark our approach on a collection of real-world and synthetic datasets, showing that it can improve performance and coverage in deep learning tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。