Related papers: Men Also Like Shopping: Reducing Gender Bias Ampli…

Modern models for common NLP tasks often employ machine learning techniques and train on journalistic, social media, or other culturally-derived text. These have recently been scrutinized for racial and gender biases, rooting from inherent…

Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender…

This study describes a procedure for applying causal modeling to detect and mitigate algorithmic bias in a multiclass classification problem. The dataset was derived from the FairFace dataset, supplemented with emotional labels generated by…

Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the representations of…

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…

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing…

Convolutional Neural Networks (CNNs) have recently emerged as the dominant model in computer vision. If provided with enough training data, they predict almost any visual quantity. In a discrete setting, such as classification, CNNs are not…

There are concerns that neural language models may preserve some of the stereotypes of the underlying societies that generate the large corpora needed to train these models. For example, gender bias is a significant problem when generating…

Automatically understanding the contents of an image is a highly relevant problem in practice. In e-commerce and social media settings, for example, a common problem is to automatically categorize user-provided pictures. Nowadays, a…

The rapid integration of Large Language Models (LLMs) into various domains raises concerns about societal inequalities and information bias. This study examines biases in LLMs related to background, gender, and age, with a focus on their…

Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent…

Coreference resolution is an important task for natural language understanding, and the resolution of ambiguous pronouns a longstanding challenge. Nonetheless, existing corpora do not capture ambiguous pronouns in sufficient volume or…

We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic…

Accurately measuring gender stereotypical bias in language models is a complex task with many hidden aspects. Current benchmarks have underestimated this multifaceted challenge and failed to capture the full extent of the problem. This…

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified…

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…

Adobe Express is expanding internationally, but the US has a disproportionately large content supply and interaction volume. Learning-to-rank (LTR) models trained primarily on behavioral feedback inherit this imbalance: templates popular in…

Bias and stereotypes in language models can cause harm, especially in sensitive areas like content moderation and decision-making. This paper addresses bias and stereotype detection by exploring how jointly learning these tasks enhances…

Language models (LMs) have become pivotal in the realm of technological advancements. While their capabilities are vast and transformative, they often include societal biases encoded in the human-produced datasets used for their training.…

It has been shown that word embeddings can exhibit gender bias, and various methods have been proposed to quantify this. However, the extent to which the methods are capturing social stereotypes inherited from the data has been debated.…