Related papers: Addressing Both Statistical and Causal Gender Fair…

Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in…

Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are…

Fair machine learning seeks to identify and mitigate biases in predictions against unfavorable populations characterized by demographic attributes, such as race and gender. Recently, a few works have extended fairness to graph data, such as…

Controlling bias in training datasets is vital for ensuring equal treatment, or parity, between different groups in downstream applications. A naive solution is to transform the data so that it is statistically independent of group…

A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has…

The importance of achieving fairness in machine learning models cannot be overstated. Recent research has pointed out that fairness should be examined from a causal perspective, and several fairness notions based on the on Pearl's causal…

Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two…

The use of machine learning models in high-stake applications (e.g., healthcare, lending, college admission) has raised growing concerns due to potential biases against protected social groups. Various fairness notions and methods have been…

Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve…

A key condition for obtaining reliable estimates of the causal effect of a treatment is overlap (a.k.a. positivity): the distributions of the features used to perform causal adjustment cannot be too different in the treated and control…

Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…

Empirical evidence suggests that algorithmic decisions driven by Machine Learning (ML) techniques threaten to discriminate against legally protected groups or create new sources of unfairness. This work supports the contextual approach to…

Most ML datasets today contain biases. When we train models on these datasets, they often not only learn these biases but can worsen them -- a phenomenon known as bias amplification. Several co-occurrence-based metrics have been proposed to…

When using machine learning to aid decision-making, it is critical to ensure that an algorithmic decision is fair and does not discriminate against specific individuals/groups, particularly those from underprivileged populations. Existing…

The influence of bias in datasets on the fairness of model predictions is a topic of ongoing research in various fields. We evaluate the performance of skin lesion classification using ResNet-based CNNs, focusing on patient sex variations…

Understanding causal mechanisms across different populations is essential for designing effective public health interventions. Recently, difference graphs have been introduced as a tool to visually represent causal variations between two…

Traditional deep learning (DL) models have two ubiquitous limitations. First, they assume training samples are independent and identically distributed (i.i.d), an assumption often violated in real-world datasets where samples have…

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

Unwanted and often harmful social biases are becoming ever more salient in NLP research, affecting both models and datasets. In this work, we ask whether training on demographically perturbed data leads to fairer language models. We collect…

Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an…