相关论文: DramatVis Personae: Visual Text Analytics for Iden…

We investigate the potential for nationality biases in natural language processing (NLP) models using human evaluation methods. Biased NLP models can perpetuate stereotypes and lead to algorithmic discrimination, posing a significant…

The rapid advancement of GenAI technology over the past few years has significantly contributed towards highly realistic deepfake content generation. Despite ongoing efforts, the research community still lacks a large-scale and reasoning…

Audio Description (AD) provides essential access to visual media for blind and low vision (BLV) audiences. Yet current AD production tools remain largely inaccessible to BLV video creators, who possess valuable expertise but face barriers…

From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a…

Open-domain dialogue generation in natural language processing (NLP) is by default a pure-language task, which aims to satisfy human need for daily communication on open-ended topics by producing related and informative responses. In this…

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…

Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer…

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to…

Because of the increasing use of data-centric systems and algorithms in machine learning, the topic of fairness is receiving a lot of attention in the academic and broader literature. This paper introduces Dbias…

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…

Image editing is an iterative process that requires precise visual evaluation and manipulation for the output to match the editing intent. However, current image editing tools do not provide accessible interaction nor sufficient feedback…

Text-to-Image (T2I) models have recently gained significant attention due to their ability to generate high-quality images and are consequently used in a wide range of applications. However, there are concerns about the gender bias of these…

Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software by generating illustrative content with high photorealism starting from a given descriptive text as…

Data visualizations are increasingly seen as socially constructed, with several recent studies positing that perceptions and interpretations of visualization artifacts are shaped through complex sets of interactions between members of a…

Vision Language Models achieve impressive multi-modal performance but often inherit gender biases from their training data. This bias might be coming from both the vision and text modalities. In this work, we dissect the contributions of…

Visual text recognition is undoubtedly one of the most extensively researched topics in computer vision. Great progress have been made to date, with the latest models starting to focus on the more practical "in-the-wild" setting. However, a…

Version identification (VI) systems now offer accurate and scalable solutions for detecting different renditions of a musical composition, allowing the use of these systems in industrial applications and throughout the wider music…

With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law…

Research on underrepresented populations is essential for fostering greater diversity within the software industry. Team diversity is important for reasons that go beyond ethics. Diversity contributes to greater innovation and productivity,…

Face verification is a significant component of identity authentication in various applications including online banking and secure access to personal devices. The majority of the existing face image datasets often suffer from notable…