Zhou Wenhao, Liu Faqiang, Zheng Hao, Zhao Rong
Center for Brain-Inspired Computing Research (CBICR), Tsinghua University, Beijing, China.
Department of Precision Instruments, Tsinghua University, Beijing, China.
Nat Commun. 2025 Jul 1;16(1):5513. doi: 10.1038/s41467-025-60801-6.
Shortcut learning poses a significant challenge to both the interpretability and robustness of artificial intelligence, arising from dataset biases that lead models to exploit unintended correlations, or shortcuts, which undermine performance evaluations. Addressing these inherent biases is particularly difficult due to the complex, high-dimensional nature of data. Here, we introduce shortcut hull learning, a diagnostic paradigm that unifies shortcut representations in probability space and utilizes diverse models with different inductive biases to efficiently learn and identify shortcuts. This paradigm establishes a comprehensive, shortcut-free evaluation framework, validated by developing a shortcut-free topological dataset to assess deep neural networks' global capabilities, enabling a shift from Minsky and Papert's representational analysis to an empirical investigation of learning capacity. Unexpectedly, our experimental results suggest that under this framework, convolutional models-typically considered weak in global capabilities-outperform transformer-based models, challenging prevailing beliefs. By enabling robust and bias-free evaluation, our framework uncovers the true model capabilities beyond architectural preferences, offering a foundation for advancing AI interpretability and reliability.
捷径学习对人工智能的可解释性和鲁棒性都构成了重大挑战，这源于数据集偏差，这些偏差会导致模型利用非预期的相关性或捷径，从而破坏性能评估。由于数据具有复杂的高维性质，解决这些内在偏差特别困难。在这里，我们引入捷径壳学习，这是一种诊断范式，它在概率空间中统一捷径表示，并利用具有不同归纳偏差的多种模型来有效学习和识别捷径。这种范式建立了一个全面的、无捷径的评估框架，通过开发一个无捷径的拓扑数据集来评估深度神经网络的全局能力进行验证，从而实现从明斯基和佩珀特的表征分析到学习能力实证研究的转变。出乎意料的是，我们的实验结果表明，在这个框架下，通常被认为在全局能力方面较弱的卷积模型优于基于Transformer的模型，这挑战了普遍的观念。通过实现强大且无偏差的评估，我们的框架揭示了超越架构偏好的真实模型能力，为推进人工智能的可解释性和可靠性提供了基础。
