但这并非原因所在：通过交互式原型修正进行推理调整
But that's not why: Inference adjustment by interactive prototype revision
AI总结：
针对机器学习模型预测可能依赖不合理因素的问题，提出基于原型部件模型的交互式推理调整方案，让非专业用户可通过识别移除缺陷原型调整推理逻辑且不损失准确率。
摘要：
尽管机器学习已取得显著进展，智能体的决策仍不完善，往往需要事后人工干预。若模型的预测依赖于不合理因素，就需要消除这些因素的影响。深度交互式原型调整使用户能够提供提示并纠正模型的推理过程。\n本文证明，原型部件模型非常适合这项任务，因为其预测基于用户可进行语义解读的原型图像块。研究表明，即便正确的分类结果，也可能依赖于由数据集中混淆变量产生的不合理原型。为此，我们提出了简单却有效的推理调整交互方案：通过交互式咨询用户来识别有缺陷的原型。非目标原型可通过原型掩码或自定义的取消选择训练模式移除。交互式原型拒绝机制让不熟悉机器学习的用户也能调整推理逻辑，且不会损害模型准确率。
英文摘要：
Despite significant advances in machine learning, decision-making of artificial agents is still not perfect and often requires post-hoc human interventions. If the prediction of a model relies on unreasonable factors it is desirable to remove their effect. Deep interactive prototype adjustment enables the user to give hints and correct the model's reasoning. In this paper, we demonstrate that prototypical-part models are well suited for this task as their prediction is based on prototypical image patches that can be interpreted semantically by the user. It shows that even correct classifications can rely on unreasonable prototypes that result from confounding variables in a dataset. Hence, we propose simple yet effective interaction schemes for inference adjustment: The user is consulted interactively to identify faulty prototypes. Non-object prototypes can be removed by prototype masking or a custom mode of deselection training. Interactive prototype rejection allows machine learning naïve users to adjust the logic of reasoning without compromising the accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
