Related papers: BLIND: Bias Removal With No Demographics
Image Restoration (IR) methods based on a pre-trained diffusion model have demonstrated state-of-the-art performance. However, they have two fundamental limitations: 1) they often assume that the degradation operator is completely known and…
Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…
We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided…
In this paper, we deal with bias mitigation techniques that remove specific data points from the training set to aim for a fair representation of the population in that set. Machine learning models are trained on these pre-processed…
Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…
Since obtaining a perfect training dataset (i.e., a dataset which is considerably large, unbiased, and well-representative of unseen cases) is hardly possible, many real-world text classifiers are trained on the available, yet imperfect,…
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth. We demonstrate that bias amplification can arise via an…
Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…
Diffusion Models are a potent class of generative models capable of producing high-quality images. However, they often inadvertently favor certain data attributes, undermining the diversity of generated images. This issue is starkly…
Biases in machine learning pose significant challenges, particularly when models amplify disparities that affect disadvantaged groups. Traditional bias mitigation techniques often lead to a {\itshape leveling-down effect}, whereby improving…
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…
This work explores the biases in learning processes based on deep neural network architectures. We analyze how bias affects deep learning processes through a toy example using the MNIST database and a case study in gender detection from…
Most positive and unlabeled data is subject to selection biases. The labeled examples can, for example, be selected from the positive set because they are easier to obtain or more obviously positive. This paper investigates how learning can…
Large Language Models (LLMs) exhibit socio-economic biases that can propagate into downstream tasks. While prior studies have questioned whether intrinsic bias in LLMs affects fairness at the downstream task level, this work empirically…
Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs, ls learns to split this dataset so that predictors…
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…
Pre-trained language models encode undesirable social biases, which are further exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating Gender Bias using Entailment Labels), an intermediate pre-training…
Artificial intelligence (AI) is increasingly being used for medical imaging tasks. However, there can be biases in AI models, particularly when they are trained using imbalanced training datasets. One such example has been the strong…
The benefits and capabilities of pre-trained language models (LLMs) in current and future innovations are vital to any society. However, introducing and using LLMs comes with biases and discrimination, resulting in concerns about equality,…
Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…