Related papers: debiaSAE: Benchmarking and Mitigating Vision-Langu…

Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the…

Advancements in Large Language Models (LLMs) have increased the performance of different natural language understanding as well as generation tasks. Although LLMs have breached the state-of-the-art performance in various tasks, they often…

Multimodal AI models capable of associating images and text hold promise for numerous domains, ranging from automated image captioning to accessibility applications for blind and low-vision users. However, uncertainty about bias has in some…

Bias in Large Language Models (LLMs) significantly undermines their reliability and fairness. We focus on a common form of bias: when two reference concepts in the model's concept space, such as sentiment polarities (e.g., "positive" and…

Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior performance. While existing…

While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set. As DMs are now widely used in real-world applications, these biases…

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a…

Purpose: Vision-language models (VLMs) have shown promising performance in surgical visual question answering (VQA). However, existing surgical VQA datasets often contain linguistic shortcuts, where question phrasing implicitly constrains…

Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well in simple single-person scenarios, in real-world…

Large language models (LLMs) have demonstrated remarkable capabilities in simulating human behaviour and social intelligence. However, they risk perpetuating societal biases, especially when demographic information is involved. We introduce…

Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technology. To remedy for…

Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual…

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the…

Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, low-resolution inputs. While recent studies have explored…

Multilingual Pre-trained Language Models (MPLMs) have become essential tools for natural language processing. However, they often exhibit biases related to sensitive attributes such as gender, race, and religion. In this paper, we introduce…

Translating natural language to visualization (NL2VIS) has shown great promise for visual data analysis, but it remains a challenging task that requires multiple low-level implementations, such as natural language processing and…

Ensuring fairness across demographic groups in medical diagnosis is essential for equitable healthcare, particularly under distribution shifts caused by variations in imaging equipment and clinical practice. Vision-language models (VLMs)…

Audio deepfake detection systems are increasingly deployed in high-stakes security applications, yet their fairness across demographic groups remains critically underexamined. Prior work measures gender disparity but does not investigate…

Image classification benchmark datasets such as CIFAR, MNIST, and ImageNet serve as critical tools for model evaluation. However, despite the cleaning efforts, these datasets still suffer from pervasive noisy labels and often contain…

There have been growing concerns around high-stake applications that rely on models trained with biased data, which consequently produce biased predictions, often harming the most vulnerable. In particular, biased medical data could cause…