Related papers: Men Also Like Shopping: Reducing Gender Bias Ampli…

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

Incidental supervision from language has become a popular approach for learning generic visual representations that can be prompted to perform many recognition tasks in computer vision. We conduct an in-depth exploration of the CLIP model…

The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…

We evaluate the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for biases related to the marking of age, gender, and race or ethnicity. Given the option to label an image as "a photo of a…

Critical scholarship has elevated the problem of gender bias in data sets used to train virtual assistants (VAs). Most work has focused on explicit biases in language, especially against women, girls, femme-identifying people, and…

Large Language Models (LLMs) often exhibit gender bias, resulting in unequal treatment of male and female subjects across different contexts. To address this issue, we propose a novel data generation framework that fosters exploratory…

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in…

Multi-label classification (MLC) is an ML task of predictive modeling in which a data instance can simultaneously belong to multiple classes. MLC is increasingly gaining interest in different application domains such as text mining,…

Machine learning (ML) technologies are known to be riddled with ethical and operational problems, however, we are witnessing an increasing thrust by businesses to deploy them in sensitive applications. One major issue among many is that ML…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision & Language Large…

Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evaluating gender bias through coreference resolution, where…

We present a large, multilingual study into how vision constrains linguistic choice, covering four languages and five linguistic properties, such as verb transitivity or use of numerals. We propose a novel method that leverages existing…

Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics…

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…

AI-based systems such as language models have been shown to replicate and even amplify social biases reflected in their training data. Among other questionable behaviors, this can lead to AI-generated text--and text suggestions--that…

Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists: the sexual objectification of girls and women, which…