Related papers: A Robust Bias Mitigation Procedure Based on the St…

Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve…

Recent text-conditioned image generation models have demonstrated an exceptional capacity to produce diverse and creative imagery with high visual quality. However, when pre-trained on billion-sized datasets randomly collected from the…

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…

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…

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…

This paper explores an empirical approach to learn more discriminantive sentence representations in an unsupervised fashion. Leveraging semantic graph smoothing, we enhance sentence embeddings obtained from pretrained models to improve…

Recent breakthroughs in self supervised training have led to a new class of pretrained vision language models. While there have been investigations of bias in multimodal models, they have mostly focused on gender and racial bias, giving…

Self-supervised learning (SSL) speech models have achieved remarkable performance in various tasks, yet the biased outcomes, especially affecting marginalized groups, raise significant concerns. Social bias refers to the phenomenon where…

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

Language carries implicit human biases, functioning both as a reflection and a perpetuation of stereotypes that people carry with them. Recently, ML-based NLP methods such as word embeddings have been shown to learn such language biases…

Previous studies have established that language models manifest stereotyped biases. Existing debiasing strategies, such as retraining a model with counterfactual data, representation projection, and prompting often fail to efficiently…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

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…

Recently, language models have demonstrated strong performance on various natural language understanding tasks. Language models trained on large human-generated corpus encode not only a significant amount of human knowledge, but also the…

Concept Bottleneck Models (CBMs) provide inherent interpretability by first predicting a set of human-understandable concepts and then mapping them to labels through a simple classifier. While users can intervene in the concept space to…

Social categories and stereotypes are embedded in language and can introduce data bias into Large Language Models (LLMs). Despite safeguards, these biases often persist in model behavior, potentially leading to representational harm in…

Word embeddings derived from human-generated corpora inherit strong gender bias which can be further amplified by downstream models. Some commonly adopted debiasing approaches, including the seminal Hard Debias algorithm, apply…