相关论文: The Authors Matter: Understanding and Mitigating I…

Recent progress in Text-to-Image (T2I) generative models has enabled high-quality image generation. As performance and accessibility increase, these models are gaining significant attraction and popularity: ensuring their fairness and…

Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

With the rapid growth in language processing applications, fairness has emerged as an important consideration in data-driven solutions. Although various fairness definitions have been explored in the recent literature, there is lack of…

Natural Language Processing technology has advanced vastly in the past decade. Text processing has been successfully applied to a wide variety of domains. In this paper, we propose a novel framework, Text Based Classification(TBC), that…

Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world. A critical question then recently arised among the population: Do algorithmic decisions convey any type of…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although…

The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning…

Ensuring fairness in machine learning is a critical and challenging task, as biased data representations often lead to unfair predictions. To address this, we propose Deep Fair Learning, a framework that integrates nonlinear sufficient…

Many studies have shown various biases targeting different demographic groups in language models, amplifying discrimination and harming fairness. Recent parameter modification debiasing approaches significantly degrade core capabilities…

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…

Language Representation Models (LRMs) trained with real-world data may capture and exacerbate undesired bias and cause unfair treatment of people in various demographic groups. Several techniques have been investigated for applying…

Machine learning systems often acquire biases by leveraging undesired features in the data, impacting accuracy variably across different sub-populations. Current understanding of bias formation mostly focuses on the initial and final stages…

We report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class classification tasks. A statistical…

The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to numerous debiasing methods targeting word level, there has been relatively less attention on biases…

State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to identifying faces. However, the implicit encoding of gender…

Machine learned models exhibit bias, often because the datasets used to train them are biased. This presents a serious problem for the deployment of such technology, as the resulting models might perform poorly on populations that are…

This paper reveals a data bias issue that can severely affect the performance while conducting a machine learning model for malicious URL detection. We describe how such bias can be identified using interpretable machine learning…

Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debiasing methods, such as…