Arondight: Red teaming large vision language models with auto-generated multi-modal jailbreak prompts

Y Liu, C Cai, X Zhang, X Yuan, C Wang - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of
Large Language Models (LLMs). Despite offering new possibilities for LLM applications …

Foodieqa: A multimodal dataset for fine-grained understanding of chinese food culture

W Li, X Zhang, J Li, Q Peng, R Tang, L Zhou… - arxiv preprint arxiv …, 2024 - arxiv.org
Food is a rich and varied dimension of cultural heritage, crucial to both individuals and
social groups. To bridge the gap in the literature on the often-overlooked regional diversity in …

Survey of cultural awareness in language models: Text and beyond

S Pawar, J Park, J **, A Arora, J Myung… - arxiv preprint arxiv …, 2024 - arxiv.org
Large-scale deployment of large language models (LLMs) in various applications, such as
chatbots and virtual assistants, requires LLMs to be culturally sensitive to the user to ensure …

Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts

EZ Zeng, Y Chen, A Wong - arxiv preprint arxiv:2410.21314, 2024 - arxiv.org
Recent advances in image generation have made diffusion models powerful tools for
creating high-quality images. However, their iterative denoising process makes …