We generalize the notion of social biases from language embeddings to grounded vision
and language embeddings. Biases are present in grounded embeddings, and indeed seem …

In recent years, the rapid advancement of machine learning (ML) models, particularly
transformer-based pre-trained models, has revolutionized Natural Language Processing …

Machine learning models have been shown to inherit biases from their training datasets.
This can be particularly problematic for vision-language foundation models trained on …

Numerous works have analyzed biases in vision and pre-trained language models
individually-however, less attention has been paid to how these biases interact in …

Vision-language models can encode societal biases and stereotypes, but there are
challenges to measuring and mitigating these multimodal harms due to lacking …

Intersectional bias is a bias caused by an overlap of multiple social factors like gender,
sexuality, race, disability, religion, etc. A recent study has shown that word embedding …

Word embeddings are a widely used set of natural language processing techniques that
map words to vectors of real numbers. These vectors are used to improve the quality of …

With the starting point that implicit human biases are reflected in the statistical regularities of
language, it is possible to measure biases in English static word embeddings. State-of-the …

We propose to learn word embeddings from visual co-occurrences. Two words co-occur
visually if both words apply to the same image or image region. Specifically, we extract four …

Language representations are known to carry stereotypical biases and, as a result, lead to
biased predictions in downstream tasks. While existing methods are effective at mitigating …