Related papers: Mitigating Gender Bias Amplification in Distributi…

In real-world machine learning systems, labels are often derived from user behaviors that the system wishes to encourage. Over time, new models must be trained as new training examples and features become available. However, feedback loops…

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

This paper presents research uncovering systematic gender bias in the representation of political leaders in the media, using artificial intelligence. Newspaper coverage of Irish ministers over a fifteen year period was gathered and…

Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We study to what extent the simplest projective debiasing methods,…

Resolving disagreement in manual annotation typically consists of removing unreliable annotators and using a label aggregation strategy such as majority vote or expert opinion to resolve disagreement. These may have the side-effect of…

Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these…

The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which…

With the proliferation of social media, there has been a sharp increase in offensive content, particularly targeting vulnerable groups, exacerbating social problems such as hatred, racism, and sexism. Detecting offensive language use is…

This study addresses gender bias in image generation models using Reinforcement Learning from Artificial Intelligence Feedback (RLAIF) with a novel Denoising Diffusion Policy Optimization (DDPO) pipeline. By employing a pretrained stable…

Pre-trained models have revolutionized natural language understanding. However, researchers have found they can encode artifacts undesired in many applications, such as professions correlating with one gender more than another. We explore…

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other…

The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…

To recognize and mitigate the harms of generative AI systems, it is crucial to consider whether and how different societal groups are represented by these systems. A critical gap emerges when naively measuring or improving who is…

Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in…

Biases in culture, gender, ethnicity, etc. have existed for decades and have affected many areas of human social interaction. These biases have been shown to impact machine learning (ML) models, and for natural language processing (NLP),…

The flow of information reaching us via the online media platforms is optimized not by the information content or relevance but by popularity and proximity to the target. This is typically performed in order to maximise platform usage. As a…

Detecting and mitigating harmful biases in modern language models are widely recognized as crucial, open problems. In this paper, we take a step back and investigate how language models come to be biased in the first place. We use a…

Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity…

Concerns regarding the footprint of societal biases in information retrieval (IR) systems have been raised in several previous studies. In this work, we examine various recent IR models from the perspective of the degree of gender bias in…

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are…