Related papers: Controlling Bias Exposure for Fair Interpretable P…

AI systems frequently exhibit and amplify social biases, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to learn a feature neuron encoding societal…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

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…

In medical image analysis, model predictions can be affected by sensitive attributes, such as race and gender, leading to fairness concerns and potential biases in diagnostic outcomes. To mitigate this, we present a causal modeling…

Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. We propose a novel task of exploring fairness on a multimodal clinical dataset, adopting equalized…

Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…

Recommendation systems play a crucial role in our daily lives by impacting user experience across various domains, including e-commerce, job advertisements, entertainment, etc. Given the vital role of such systems in our lives,…

What does it mean for an algorithm to be biased? In U.S. law, unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral.…

We study fairness in supervised few-shot meta-learning models that are sensitive to discrimination (or bias) in historical data. A machine learning model trained based on biased data tends to make unfair predictions for users from minority…

Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data…

Deep learning has produced big advances in artificial intelligence, but trained neural networks often reflect and amplify bias in their training data, and thus produce unfair predictions. We propose a novel measure of individual fairness,…

Debiasing methods that seek to mitigate the tendency of Language Models (LMs) to occasionally output toxic or inappropriate text have recently gained traction. In this paper, we propose a standardized protocol which distinguishes methods…

Language data and models demonstrate various types of bias, be it ethnic, religious, gender, or socioeconomic. AI/NLP models, when trained on the racially biased dataset, AI/NLP models instigate poor model explainability, influence user…

Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier. For example, in some applications, a classifier may not have direct access to sensitive attributes,…

Dataset bias is a critical challenge in machine learning since it often leads to a negative impact on a model due to the unintended decision rules captured by spurious correlations. Although existing works often handle this issue based on…

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

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…

Learning a fair predictive model is crucial to mitigate biased decisions against minority groups in high-stakes applications. A common approach to learn such a model involves solving an optimization problem that maximizes the predictive…

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an…

Link prediction is a crucial task in network analysis, but it has been shown to be prone to biased predictions, particularly when links are unfairly predicted between nodes from different sensitive groups. In this paper, we study the fair…