过度同质化：从算法到人类在学习弃权（不执行）中的偏见
Too Much of the Same: From Algorithmic to Human Bias in Learning to Defer
浏览论文内容
中文总结 AI 辅助
该研究针对学习弃权（LtD）策略，发现其存在类别依赖采样偏见，会引发人类认知偏见，经226人用户研究验证，不平衡弃权集会降低多数类分类准确率，探讨了相关部署意义。
中文摘要 AI 辅助
学习弃权（LtD）是对监督学习的扩展，它允许机器学习（ML）模型将更困难或置信度较低的决策弃权（不执行）给人类专家。尽管LtD旨在用于人机协作，但LtD策略忽略了人类认知偏见可能带来的负面干扰。我们的贡献有两点：第一，我们证明标准LtD策略在实践中会在分类任务中表现出依赖类别的采样偏见，因此当应用于不平衡数据集时，可能会不成比例地将少数类别的决策弃权（不执行）出去；第二，我们表明这种任务委托中的不对称性可能会引发人类偏见，最终导致下游决策质量下降。具体而言，我们开展了一项用户研究（N=226），参与者对一组被弃权（不执行）的项目完成分类任务，研究条件呈现不同程度的类别不平衡。结果显示，无论哪个类别构成多数类，接触高度不平衡弃权集的参与者在多数类上的分类准确率低于接触更平衡弃权集的参与者。探索性分析表明，这可能是考生效应的一个实例，该效应源于类别的实际分布与参与者对该分布的预期不匹配。最后，我们讨论了这些发现对LtD算法部署的意义。
英文摘要
Learning to Defer (LtD) extends supervised learning by allowing a Machine Learning (ML) model to defer harder or less confident decisions to a human expert. Despite being geared for human-AI collaboration, LtD strategies neglect the potential negative interference of human cognitive biases. Our contribution is twofold. First, we demonstrate that standard LtD strategies show class-dependent sampling bias in classification tasks in practice, and thus may disproportionately defer the minority classes when applied to imbalanced datasets. Second, we show that such asymmetries in task delegation may trigger human biases, ultimately leading to poorer downstream decision making. Specifically, we conduct a user study ($N=226$) where participants complete a classification task on a set of deferred items, with conditions presenting different levels of class imbalance. Our results show that participants exposed to a highly imbalanced rejection set achieved lower classification accuracy in the majority class compared to those exposed to a more balanced set, regardless of which class constituted the majority. Exploratory analyses suggest that this may be an instance of the Test-taker's effect, which stems from a mismatch between the actual distribution of classes and the participants' expectations about that distribution. Finally, we discuss the implications of these findings for the deployment of LtD algorithms.
