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

We propose a novel taxonomy for bias evaluation of discriminative foundation models, such as Contrastive Language-Pretraining (CLIP), that are used for labeling tasks. We then systematically evaluate existing methods for mitigating bias in…

Performance disparities of image recognition across demographic groups are known to exist in deep learning-based models, due to imbalanced group representations or spurious correlation between group and target labels. Previous work has…

Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses are influenced by societal biases present in their training…

Vision-language models (VLMs) have demonstrated remarkable progress in multimodal reasoning. However, existing benchmarks remain limited in terms of high-quality, human-verified examples. Many current datasets rely on synthetically…

Language model debiasing has emerged as an important field of study in the NLP community. Numerous debiasing techniques were proposed, but bias ablation remains an unaddressed issue. We demonstrate a novel framework for inspecting bias in…

As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms. Many datasets for measuring bias currently…

In practice, and especially when training deep neural networks, visual recognition rules are often learned based on various sources of information. On the other hand, the recent deployment of facial recognition systems with uneven…

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often exhibit a tendency to…

Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. This underscores the critical need for dataset pruning, as the quality of these datasets is strongly correlated with the performance of VLMs on…

Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue…

Recent advancements in Large Language Models (LLMs) have positioned them as powerful tools for clinical decision-making, with rapidly expanding applications in healthcare. However, concerns about bias remain a significant challenge in the…

Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although…

Gender bias in vision-language models (VLMs) can reinforce harmful stereotypes and discrimination. In this paper, we focus on mitigating gender bias towards vision-language tasks. We identify object hallucination as the essence of gender…

Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for…

Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization…

Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its…

Vision Language Models (VLMs) are pivotal for advancing perception in intelligent agents. Yet, evaluation of VLMs remains limited to predominantly English-centric benchmarks in which the image-text pairs comprise short texts. To evaluate…

Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

In the realms of computer vision and natural language processing, Multimodal Large Language Models (MLLMs) have become indispensable tools, proficient in generating textual responses based on visual inputs. Despite their advancements, our…