Related papers: Leveraging Prototypical Representations for Mitiga…

Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

We propose an approach for unsupervised domain adaptation for the task of estimating someone's age from a given face image. In order to avoid the propagation of racial bias in most publicly available face image datasets into the inefficacy…

Gender classification systems often inherit and amplify demographic imbalances in their training data. We first audit five widely used gender classification datasets, revealing that all suffer from significant intersectional…

Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This is particularly concerning with the increasing use of large, unsupervised datasets for training foundational…

Large Language Models (LLMs) have been observed to exhibit bias in numerous ways, potentially creating or worsening outcomes for specific groups identified by protected attributes such as sex, race, sexual orientation, or age. To help…

Large language models (LLMs) trained on vast corpora suffer from inevitable stereotype biases. Mitigating these biases with fine-tuning could be both costly and data-hungry. Model editing methods, which focus on modifying LLMs in a post-hoc…

Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresented in the training data. In this paper, we leverage this…

Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first…

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…

Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on…

Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice.…

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…

Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation…

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…

Fair machine learning methods seek to train models that balance model performance across demographic subgroups defined over sensitive attributes like race and gender. Although sensitive attributes are typically assumed to be known during…

Ensuring fairness in machine learning predictions is a critical challenge, especially when models are deployed in sensitive domains such as credit scoring, healthcare, and criminal justice. While many fairness interventions rely on data…

Growing concerns regarding algorithmic fairness have led to a surge in methodologies to mitigate algorithmic bias. However, such methodologies largely assume that observed labels in training data are correct. This is problematic because…

Mitigating bias in language models (LMs) has become a critical problem due to the widespread deployment of LMs. Numerous approaches revolve around data pre-processing and fine-tuning of language models, tasks that can be both time-consuming…

Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…