Related papers: Improving Bias Mitigation through Bias Experts in …

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…

Deep image classifiers have been found to learn biases from datasets. To mitigate the biases, most previous methods require labels of protected attributes (e.g., age, skin tone) as full-supervision, which has two limitations: 1) it is…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

In image classification, "debiasing" aims to train a classifier to be less susceptible to dataset bias, the strong correlation between peripheral attributes of data samples and a target class. For example, even if the frog class in the…

Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain…

Neural networks are prone to be biased towards spurious correlations between classes and latent attributes exhibited in a major portion of training data, which ruins their generalization capability. We propose a new method for training…

Image classifiers often rely overly on peripheral attributes that have a strong correlation with the target class (i.e., dataset bias) when making predictions. Due to the dataset bias, the model correctly classifies data samples including…

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

The performance of algorithmic decision rules is largely dependent on the quality of training datasets available to them. Biases in these datasets can raise economic and ethical concerns due to the resulting algorithms' disparate treatment…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the…

Spurious correlations in training data significantly hinder the generalization capability of machine learning models when faced with distribution shifts, leading to the proposition of numberous debiasing methods. However, it remains to be…

Neural networks often learn spurious correlations when exposed to biased training data, leading to poor performance on out-of-distribution data. A biased dataset can be divided, according to biased features, into bias-aligned samples (i.e.,…

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…