Related papers: Discovering Bias in Latent Space: An Unsupervised …

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Deep neural networks trained on biased data often inadvertently learn unintended inference rules, particularly when labels are strongly correlated with biased features. Existing bias mitigation methods typically involve either a)…

Stance detection models may tend to rely on dataset bias in the text part as a shortcut and thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing methods usually treated features learned by small…

Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its…

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we…

Numerous methods have been implemented that pursue fairness with respect to sensitive features by mitigating biases in machine learning. Yet, the problem settings that each method tackles vary significantly, including the stage of…

Diffusion models steer conditional generation with a tunable guidance scale to trade off prompt alignment and diversity. However, existing debiasing techniques are optimized for a single scale, degrading fairness when users adjust this…

The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such as integrating any source of signal to estimate unknown…

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information 'fairly,' with…

In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, resulting in lack of reliability of the model trained on…

The label bias and selection bias are acknowledged as two reasons in data that will hinder the fairness of machine-learning outcomes. The label bias occurs when the labeling decision is disturbed by sensitive features, while the selection…

Foundation models have emerged as robust models with label efficiency in diverse domains. In medical imaging, these models contribute to the advancement of medical diagnoses due to the difficulty in obtaining labeled data. However, it is…

Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…

The biases and discrimination of machine learning algorithms have attracted significant attention, leading to the development of various algorithms tailored to specific contexts. However, these solutions often fall short of addressing…

Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by…

Removing bias while keeping all task-relevant information is challenging for fair representation learning methods since they would yield random or degenerate representations w.r.t. labels when the sensitive attributes correlate with labels.…