Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut features is not fully understood, and algorithms to mitigate this behavior rely on as yet unjustified assumptions about the learned representations. In this work, we provide the first end-to-end theoretical characterization of spurious feature learning for two-layer ReLU neural networks trained by online minibatch SGD on the logistic loss. We consider data drawn from the high-dimensional Boolean hypercube with a quadratic signal function (namely XOR) and a linear spurious correlation. We show that SGD learns the spurious feature first, and exponentially fast. Moreover, the optimization dynamics couple the spurious and signal features, with a stronger spurious component inhibiting signal feature learning. Our analysis reveals precise phase transitions in the learning dynamics. In the first phase, alignment between the signs of the spurious feature and second-layer weight drives rapid growth of the spurious feature. In the second phase, large majority group margin slows learning and the signal feature remains suppressed. When the spurious correlation is maximally strong, we show theoretically that the spurious feature dominates even at the sample complexity threshold where XOR would be learned in isolation (i.e., if the spurious feature was absent). In contrast, when the correlation strength is constant, we provide preliminary empirical evidence that the model can eventually learn the XOR signal, although the spurious feature is not forgotten.

Single-source Domain Generalized Object Detection (SDGOD), as a cutting-edge research topic in computer vision, aims to enhance model generalization capability in unseen target domains through single-source domain training. Current mainstream approaches attempt to mitigate domain discrepancies via data augmentation techniques. However, due to domain shift and limited domain-specific knowledge, models tend to fall into the pitfall of spurious correlations. This manifests as the model's over-reliance on simplistic classification features (e.g., color) rather than essential domain-invariant representations like object contours. To address this critical challenge, we propose the Cauvis (Causal Visual Prompts) method. First, we introduce a Cross-Attention Prompts module that mitigates bias from spurious features by integrating visual prompts with cross-attention. To address the inadequate domain knowledge coverage and spurious feature entanglement in visual prompts for single-domain generalization, we propose a dual-branch adapter that disentangles causal-spurious features while achieving domain adaptation via high-frequency feature extraction. Cauvis achieves state-of-the-art performance with 15.9-31.4% gains over existing domain generalization methods on SDGOD datasets, while exhibiting significant robustness advantages in complex interference environments.

Benchmarks for out-of-distribution (OOD) generalization frequently show a strong positive correlation between in-distribution (ID) and OOD accuracy across models, termed "accuracy-on-the-line." This pattern is often taken to imply that spurious correlations--correlations that improve ID but reduce OOD performance--are rare in practice. We find that this positive correlation is often an artifact of aggregating heterogeneous OOD examples. Using a simple gradient-based method, OODSelect, we identify semantically coherent OOD subsets where accuracy on the line does not hold. Across widely used distribution shift benchmarks, the OODSelect uncovers subsets, sometimes up to over half of the standard OOD set, where higher ID accuracy predicts lower OOD accuracy. Our findings indicate that aggregate metrics can obscure important failure modes of OOD robustness. We release code and the identified subsets to facilitate further research.

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (stochastic) gradient descent (GD), remains limited. In practice, neural networks (NNs) trained with SGD are known to exhibit simplicity bias -- a tendency to find simple solutions. In contrast, we show that Adam is more resistant to such simplicity bias. First, we investigate the differences in the implicit biases of Adam and GD when training two-layer ReLUNNs on a binary classification task with Gaussian data. We find that GD exhibits a simplicity bias, resulting in a linear decision boundary with a suboptimal margin, whereas Adam leads to much richer and more diverse features, producing a nonlinear boundary that is closer to the Bayes' optimal predictor. This richer decision boundary also allows Adam to achieve higher test accuracy both in-distribution and under certain distribution shifts. We theoretically prove these results by analyzing the population gradients. Next, to corroborate our theoretical findings, we present extensive empirical results showing that this property of Adam leads to superior generalization across various datasets with spurious correlations where NNs trained with SGD are known to show simplicity bias and do not generalize well under certain distributional shifts.

Neural networks generally prefer simple and easy-to-learn features. When these features are spuriously correlated with the labels, the network's performance can suffer, particularly for underrepresented classes or concepts. Self-supervised representation learning methods, such as contrastive learning, are especially prone to this issue, often resulting in worse performance on downstream tasks. We identify a key spectral signature of this failure: early reliance on dominant singular modes of the learned feature matrix. To mitigate this, we propose a novel framework that promotes a uniform eigenspectrum of the feature covariance matrix, encouraging diverse and semantically rich representations. Our method operates in a fully self-supervised setting, without relying on ground-truth labels or any additional information. Empirical results on SimCLR and SimSiam demonstrate consistent gains in robustness and transfer performance, suggesting broad applicability across self-supervised learning paradigms.

For an LLM to correctly respond to an instruction it must understand both the semantics and the domain (i.e., subject area) of a given task-instruction pair. However, syntax can also convey implicit information. Recent work shows that syntactic templates--frequent sequences of Part-of-Speech (PoS) tags--are prevalent in training data and often appear in model outputs. In this work we characterize syntactic templates, domain, and semantics in task-instruction pairs. We identify cases of spurious correlations between syntax and domain, where models learn to associate a domain with syntax during training; this can sometimes override prompt semantics.

Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications, where they frequently face data distributions unseen during training. Despite progress, existing methods are often vulnerable to spurious correlations that mislead models and compromise robustness. To address this, we propose SPROD, a novel prototype-based OOD detection approach that explicitly addresses the challenge posed by unknown spurious correlations. Our post-hoc method refines class prototypes to mitigate bias from spurious features without additional data or hyperparameter tuning, and is broadly applicable across diverse backbones and OOD detection settings. We conduct a comprehensive spurious correlation OOD detection benchmarking, comparing our method against existing approaches and demonstrating its superior performance across challenging OOD datasets, such as CelebA, Waterbirds, UrbanCars, Spurious Imagenet, and the newly introduced Animals MetaCoCo. On average, SPROD improves AUROC by 4.8% and FPR@95 by 9.4% over the second best.

Spurious correlations occur when models rely on non-essential features that coincidentally co-vary with target labels, leading to incorrect reasoning under distribution shift. We consider spurious correlations in Large Vision Language Models (LVLMs) pretrained on extensive and diverse datasets without explicit task supervision. We develop a benchmark by sourcing GPT-4o errors on real-world visual-question-answering (VQA) benchmarks, then curating a subset through LVLM-human annotation and synthetic counterfactual evaluation to identify errors caused by spurious correlations. This process yields SpuriVerse, a novel benchmark comprised of 124 distinct types of spurious correlations extracted from real-world datasets, each containing 1 realistic and 10 synthetic VQA samples for a total of 1364 multiple choice questions. We evaluate 15 open and closed-source LVLMs on SpuriVerse, finding that even state-of-the-art closed-source models struggle significantly, achieving at best only 35.0% accuracy. Fine-tuning on synthetic examples that emphasize the spurious correlation improves performance to 78.4%, suggesting that training on diverse spurious patterns generalizes to unseen situations: models appear to learn to avoid "shortcuts" and attend to the overall image context.

Neurosymbolic AI is growing in popularity thanks to its ability to combine neural perception and symbolic reasoning in end-to-end trainable models. However, recent findings reveal these are prone to shortcut reasoning, i.e., to learning unindented concepts--or neural predicates--which exploit spurious correlations to satisfy the symbolic constraints. In this paper, we address reasoning shortcuts at their root cause and we introduce Prototypical Neurosymbolic architectures. These models are able to satisfy the symbolic constraints (be right) because they have learnt the correct basic concepts (for the right reasons) and not because of spurious correlations, even in extremely low data regimes. Leveraging the theory of prototypical learning, we demonstrate that we can effectively avoid reasoning shortcuts by training the models to satisfy the background knowledge while taking into account the similarity of the input with respect to the handful of labelled datapoints. We extensively validate our approach on the recently proposed rsbench benchmark suite in a variety of settings and tasks with very scarce supervision: we show significant improvements in learning the right concepts both in synthetic tasks (MNIST-EvenOdd and Kand-Logic) and real-world, high-stake ones (BDD-OIA). Our findings pave the way to prototype grounding as an effective, annotation-efficient strategy for safe and reliable neurosymbolic learning.

The rapid increase in AI-generated images (AIGIs) underscores the need for detection methods. Existing detectors are often trained on biased datasets, leading to overfitting on spurious correlations between non-causal image attributes and real/synthetic labels. While these biased features enhance performance on the training data, they result in substantial performance degradation when tested on unbiased datasets. A common solution is to perform data alignment through generative reconstruction, matching the content between real and synthetic images. However, we find that pixel-level alignment alone is inadequate, as the reconstructed images still suffer from frequency-level misalignment, perpetuating spurious correlations.