Related papers: A Systematic Study of Bias Amplification
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias.…
Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people. To mitigate the bias of…
A machine learning model is calibrated if its predicted probability for an outcome matches the observed frequency for that outcome conditional on the model prediction. This property has become increasingly important as the impact of machine…
In this paper, we propose a new framework for mitigating biases in machine learning systems. The problem of the existing mitigation approaches is that they are model-oriented in the sense that they focus on tuning the training algorithms to…
The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…
Despite numerous efforts to mitigate their biases, ML systems continue to harm already-marginalized people. While predominant ML approaches assume bias can be removed and fair models can be created, we show that these are not always…
Despite the constant development of new bias mitigation methods for machine learning, no method consistently succeeds, and a fundamental question remains unanswered: when and why do bias mitigation techniques fail? In this paper, we…
Machine learning actively impacts our everyday life in almost all endeavors and domains such as healthcare, finance, and energy. As our dependence on the machine learning increases, it is inevitable that these algorithms will be used to…
If a model has some behavioral tendency, such as sycophancy or misalignment, and it is trained on its own outputs, will the tendency be amplified in the next generation of models? We study this question by training a series of models where…
Individual and social biases undermine the effectiveness of human advisers by inducing judgment errors which can disadvantage protected groups. In this paper, we study the influence these biases can have in the pervasive problem of fake…
The problem of algorithmic bias in machine learning has gained a lot of attention in recent years due to its concrete and potentially hazardous implications in society. In much the same manner, biases can also alter modern industrial and…
The underlying paradigm of big data-driven machine learning reflects the desire of deriving better conclusions from simply analyzing more data, without the necessity of looking at theory and models. Is having simply more data always…
Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias".…
Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a…
Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…
Human society had a long history of suffering from cognitive biases leading to social prejudices and mass injustice. The prevalent existence of cognitive biases in large volumes of historical data can pose a threat of being manifested as…
We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to…
Many capable large language models (LLMs) are developed via self-supervised pre-training followed by a reinforcement-learning fine-tuning phase, often based on human or AI feedback. During this stage, models may be guided by their inductive…
Artificial Intelligence has the potential to exacerbate societal bias and set back decades of advances in equal rights and civil liberty. Data used to train machine learning algorithms may capture social injustices, inequality or…
Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets. We present a technique for certifying whether linear regression models are…