1 code implementation • 2 Jul 2024 • Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime.
no code implementations • 2 Jul 2024 • Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu
We propose a unique debiasing technique, Social Contact Debiasing (SCD), that instruction-tunes these models with unbiased responses to prompts.
1 code implementation • 2 Jul 2024 • Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos
We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated by DALL-E 3 and validated by humans, containing 9, 935 images of 67 countries and 10 concept classes; (2) the underlying implicit and potentially stereotypical cultural associations with a cultural artifact extraction task; and (3) an approach to adapt cultural representation in an image based on extracted associations using a modular pipeline, CultureAdapt.
1 code implementation • 26 Oct 2023 • Anjishnu Mukherjee, Chahat Raj, Ziwei Zhu, Antonios Anastasopoulos
Finally, we highlight the significance of these social biases and the new dimensions through an extensive comparison of embedding methods, reinforcing the need to address them in pursuit of more equitable language models.
