Large language models (LLMs) demonstrate emergent in-context learning capabilities,
where they adapt to new tasks based on example demonstrations. However, in-context …

Machine learning systems are known to be sensitive to spurious correlations between non-
essential features of the inputs (eg, background, texture, and secondary objects) and the …

Empirical risk minimization (ERM) is sensitive to spurious correlations present in training
data, which poses a significant risk when deploying systems trained under this paradigm in …

Machine learning algorithms learned from data with skewed distributions usually suffer from
poor generalization, especially when minority classes matter as much as, or even more than …

Radiotherapy treatment planning is a time-consuming and potentially subjective process
that requires the iterative adjustment of model parameters to balance multiple conflicting …

Neural networks often learn simple explanations that fit the majority of the data while
memorizing exceptions that deviate from these explanations. This behavior leads to poor …

Spurious patterns refer to a mathematical association between two or more variables in a
dataset that are not causally related. However, this notion of spuriousness, which is usually …

Models trained with empirical risk minimization (ERM) are prone to be biased towards
spurious correlations between target labels and bias attributes, which leads to poor …

In the real world, data often follows a long-tailed distribution, resulting in head classes
receiving more attention while tail classes are frequently overlooked. Although supervised …

In this work, we tackle a challenging and extreme form of subpopulation shift, which is
termed compositional shift. Under compositional shifts, some combinations of attributes are …