Related papers: Bias in Text Embedding Models
Non-contextual word embedding models have been shown to inherit human-like stereotypical biases of gender, race and religion from the training corpora. To counter this issue, a large body of research has emerged which aims to mitigate these…
Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically. However, these AI models also learn gender, racial and…
Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information. However, it can suffer from biases that harm users and society at large. As a…
With the growing adoption of Text-to-Image (TTI) systems, the social biases of these models have come under increased scrutiny. Herein we conduct a systematic investigation of one such source of bias for diffusion models: embedding spaces.…
Multilingual Neural Machine Translation architectures mainly differ in the amount of sharing modules and parameters among languages. In this paper, and from an algorithmic perspective, we explore if the chosen architecture, when trained…
Our society is plagued by several biases, including racial biases, caste biases, and gender bias. As a matter of fact, several years ago, most of these notions were unheard of. These biases passed through generations along with…
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior…
Large Language Models (LLMs) have made substantial progress in the past several months, shattering state-of-the-art benchmarks in many domains. This paper investigates LLMs' behavior with respect to gender stereotypes, a known issue for…
With language models being deployed increasingly in the real world, it is essential to address the issue of the fairness of their outputs. The word embedding representations of these language models often implicitly draw unwanted…
Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the…
We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms like Hugging Face. While these platforms democratize AI, they also facilitate the spread of…
Text-to-image (T2I) generative models are largely used in AI-powered real-world applications and value creation. However, their strategic deployment raises critical concerns for responsible AI management, particularly regarding the…
Social biases are encoded in word embeddings. This presents a unique opportunity to study society historically and at scale, and a unique danger when embeddings are used in downstream applications. Here, we investigate the extent to which…
Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance…
Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP). These embeddings are learnt from data that has been gathered "from the wild" and have been found…
Machine learning models are trained to find patterns in data. NLP models can inadvertently learn socially undesirable patterns when training on gender biased text. In this work, we propose a general framework that decomposes gender bias in…
Word embeddings have been shown to produce remarkable results in tackling a vast majority of NLP related tasks. Unfortunately, word embeddings also capture the stereotypical biases that are prevalent in society, affecting the predictive…
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…
Gender bias in artificial intelligence has become an important issue, particularly in the context of language models used in communication-oriented applications. This study examines the extent to which Large Language Models (LLMs) exhibit…
It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons…