Related papers: Causal Effect Regularization: Automated Detection …
The predictions of text classifiers are often driven by spurious correlations -- e.g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this…
Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing…
Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can…
Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…
Unsupervised feature selection (UFS) has recently gained attention for its effectiveness in processing unlabeled high-dimensional data. However, existing methods overlook the intrinsic causal mechanisms within the data, resulting in the…
To capture the relationship between samples and labels, conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to…
Shortcut learning, in which models make use of easy-to-represent but unstable associations, is a major failure mode for robust machine learning. We study a flexible, causally-motivated approach to training robust predictors by discouraging…
Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In…
Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. While most existing debiasing methods require full supervision on either spurious attributes or target labels, training a debiased…
Spurious correlations are a threat to the trustworthiness of natural language processing systems, motivating research into methods for identifying and eliminating them. However, addressing the problem of spurious correlations requires more…
Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss. However, some of these features might be spuriously correlated with the target labels, leading to incorrect predictions by the…
We study attribute control in language models through the method of Causal Average Treatment Effect (Causal ATE). Existing methods for the attribute control task in Language Models (LMs) check for the co-occurrence of words in a sentence…
In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts are much larger than…
Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character; e.g., changing the gender of a…
Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP). Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and…
Much recent work in NLP has documented dataset artifacts, bias, and spurious correlations between input features and output labels. However, how to tell which features have "spurious" instead of legitimate correlations is typically left…
A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output. However, if training data contains both causal and correlational relationships, a…
Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…
The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. To resolve this, recent works focus on developing weaker…
This paper frames causal structure estimation as a machine learning task. The idea is to treat indicators of causal relationships between variables as `labels' and to exploit available data on the variables of interest to provide features…