统一分歧术语，系统梳理模型捷径问题的成因与应对方法。
Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
- 提出统一的捷径学习定义，整合多种术语和研究视角。
- 梳理检测与缓解捷径的现有方法，揭示未被充分探索的方向。
- 整理专用于研究捷径学习的数据集，助力后续实验验证。
捷径（Shortcuts），又称聪明汉现象、虚假相关或混淆因子，是机器学习与人工智能中的重大挑战，严重影响模型的泛化能力与鲁棒性。然而，该领域的研究术语分散，阻碍了整体进展。为此，本文提出一个统一的捷径学习分类体系，给出捷径的正式定义，并连接文献中使用的多样术语。同时，我们建立捷径与偏差、因果推断、安全等领域的关键关联，尽管这些联系常被忽视。本分类体系组织了现有的捷径检测与缓解方法，全面呈现当前研究现状，揭示未被充分探索的领域与开放挑战。此外，我们收集并分类了专用于研究捷径学习的数据集。综上，本工作为深入理解捷径问题提供了整体视角，推动更有效策略的发展。
原文摘要 · Abstract (English)
Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however, remains fragmented across various terminologies, hindering the progress of the field as a whole. Consequently, we introduce a unifying taxonomy of shortcut learning by providing a formal definition of shortcuts and bridging the diverse terms used in the literature. In doing so, we further establish important connections between shortcuts and related fields, including bias, causality, and security, where parallels exist but are rarely discussed. Our taxonomy organizes existing approaches for shortcut detection and mitigation, providing a comprehensive overview of the current state of the field and revealing underexplored areas and open challenges. Moreover, we compile and classify datasets tailored to study shortcut learning. Altogether, this work provides a holistic perspective to deepen understanding and drive the development of more effective strategies for addressing shortcuts in machine learning.
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。