Related papers: Debiasing Personal Identities in Toxicity Classifi…

Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to…

Supervised machine learning models and their evaluation strongly depends on the quality of the underlying dataset. When we search for a relevant piece of information it may appear anywhere in a given passage. However, we observe a bias in…

Classification is an essential and fundamental task in machine learning, playing a cardinal role in the field of natural language processing (NLP) and computer vision (CV). In a supervised learning setting, labels are always needed for the…

Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comments targeting different demographic groups can vary markedly…

In today's society, AI systems are increasingly used to make critical decisions such as credit scoring and patient triage. However, great convenience brought by AI systems comes with troubling prevalence of bias against underrepresented…

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been shown to be…

A wide range of machine learning algorithms iteratively add data to the training sample. Examples include semi-supervised learning, active learning, multi-armed bandits, and Bayesian optimization. We embed this kind of data addition into…

Binary classifiers trained on a certain proportion of positive items introduce a bias when applied to data sets with different proportions of positive items. Most solutions for dealing with this issue assume that some information on the…

One of the difficulties of artificial intelligence is to ensure that model decisions are fair and free of bias. In research, datasets, metrics, techniques, and tools are applied to detect and mitigate algorithmic unfairness and bias. This…

Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition. But do unsupervised computer vision…

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias,…

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…

The rapid growth in user generated content on social media has resulted in a significant rise in demand for automated content moderation. Various methods and frameworks have been proposed for the tasks of hate speech detection and toxic…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

This work examines how to train fair classifiers in settings where training labels are corrupted with random noise, and where the error rates of corruption depend both on the label class and on the membership function for a protected…

Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations…

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (\eg Female) within class labels $Y$ (\eg Programmers). This dataset bias can lead to models that learn spurious correlations between class…

Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities.…

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement…