Related papers: Discovering and Mitigating Visual Biases through K…

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…

Recently, many bias detection methods have been proposed to determine the level of bias a large language model captures. However, tests to identify which parts of a large language model are responsible for bias towards specific groups…

Translating information between text and image is a fundamental problem in artificial intelligence that connects natural language processing and computer vision. In the past few years, performance in image caption generation has seen…

AI algorithms are not immune to biases. Traditionally, non-experts have little control in uncovering potential social bias (e.g., gender bias) in the algorithms that may impact their lives. We present a preliminary design for an interactive…

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

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…

Detecting biases in artificial intelligence has become difficult because of the impenetrable nature of deep learning. The central difficulty is in relating unobservable phenomena deep inside models with observable, outside quantities that…

Text-to-image (T2I) models, and their encoded biases, increasingly shape the visual media the public encounters. While researchers have produced a rich body of work on bias measurement, auditing, and mitigation in T2I systems, those methods…

Text-to-image (T2I) diffusion models have revolutionized generative modeling by producing high-fidelity, diverse, and visually realistic images from textual prompts. Despite these advances, existing models struggle with complex prompts…

This paper examines potential biases and inconsistencies in emotional evocation of images produced by generative artificial intelligence (AI) models and their potential bias toward negative emotions. In particular, we assess this bias by…

Bias is a common problem in today's media, appearing frequently in text and in visual imagery. Users on social media websites such as Twitter need better methods for identifying bias. Additionally, activists --those who are motivated to…

Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different…

While existing image-text alignment models reach high quality binary assessments, they fall short of pinpointing the exact source of misalignment. In this paper, we present a method to provide detailed textual and visual explanation of…

The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension - such as ethnicity or age - can inadvertently affect another, like…

Bias analysis is a crucial step in the process of creating fair datasets for training and evaluating computer vision models. The bottleneck in dataset analysis is annotation, which typically requires: (1) specifying a list of attributes…

The misuse of generative AI in online disinformation campaigns highlights the urgent need for transparent and explainable detection systems. In this work, we investigate how detectors for AI-generated images can be more effective in…

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 models can be laden with biases against intersectional…

Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples. While the problem of…

Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can…

We address the challenge of generating fair and unbiased image retrieval results given neutral textual queries (with no explicit gender or race connotations), while maintaining the utility (performance) of the underlying vision-language…