Related papers: Do Not Harm Protected Groups in Debiasing Language…
Word embedding, which converts words into numerical values, is an important natural language processing technique and widely used. One of the serious problems of word embedding is that the bias will be learned and affect the model if the…
Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality. To create interventions and mitigate these biases…
The advancement of Large Language Models (LLMs) has transformed Natural Language Processing (NLP), enabling performance across diverse tasks with little task-specific training. However, LLMs remain susceptible to social biases, particularly…
Representation bias is one of the most common types of biases in artificial intelligence (AI) systems, causing AI models to perform poorly on underrepresented data segments. Although AI practitioners use various methods to reduce…
The training of large language models (LLMs) on extensive, unfiltered corpora sourced from the internet is a common and advantageous practice. Consequently, LLMs have learned and inadvertently reproduced various types of biases, including…
Removing bias while keeping all task-relevant information is challenging for fair representation learning methods since they would yield random or degenerate representations w.r.t. labels when the sensitive attributes correlate with labels.…
We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…
The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory…
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…
Studies have shown that some Natural Language Processing (NLP) systems encode and replicate harmful biases with potential adverse ethical effects in our society. In this article, we propose an approach for identifying gender and racial…
Large language models (LLMs) are trained on extensive text corpora, which inevitably include biased information. Although techniques such as Affective Alignment can mitigate some negative impacts of these biases, existing prompt-based…
Word embeddings are the standard model for semantic and syntactic representations of words. Unfortunately, these models have been shown to exhibit undesirable word associations resulting from gender, racial, and religious biases. Existing…
Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…
Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…
As Vision Language Models (VLMs) gain widespread use, their fairness remains under-explored. In this paper, we analyze demographic biases across five models and six datasets. We find that portrait datasets like UTKFace and CelebA are the…
Image generative models, particularly diffusion-based models, have surged in popularity due to their remarkable ability to synthesize highly realistic images. However, since these models are data-driven, they inherit biases from the…
Embeddings play a pivotal role in the efficacy of Large Language Models. They are the bedrock on which these models grasp contextual relationships and foster a more nuanced understanding of language and consequently perform remarkably on a…
Bias in image restoration algorithms can hamper further analysis, typically when the intensities have a physical meaning of interest, e.g., in medical imaging. We propose to suppress a part of the bias -- the method bias -- while leaving…
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),…
In the social sciences, it is often necessary to debias studies and surveys before valid conclusions can be drawn. Debiasing algorithms enable the computational removal of bias using sample weights. However, an issue arises when only a…