Gender bias in multimodal models a transnational feminist approach considering geographical region and culture
Mandal, AbhishekORCID: 0000-0002-5275-4192, Little, SuzanneORCID: 0000-0003-3281-3471 and Leavy, SusanORCID: 0000-0002-3679-2279
(2023)
Gender bias in multimodal models a transnational feminist approach considering geographical region and culture.
In: International Workshop on Algorithmic Bias in Search and Recommendation, 2 Apr 2022, Dublin, Ireland.
ISBN 978-3-031-37248-3
Deep learning based visual-linguistic multimodal models such as Contrastive Language Image Pre-training (CLIP) have become increasingly popular recently and are used within text-to-image generative models such as DALL-E and Stable Diffusion. However, gender and other social biases have been uncovered in these models, and this has the potential to be amplified and perpetuated through AI systems. In this paper, we present a methodology for auditing multimodal models that consider gender, informed
by concepts from transnational feminism, including regional and cultural dimensions. Focusing on CLIP, we found evidence of significant gender bias with varying patterns across global regions. Harmful stereotypical associations were also uncovered related to visual cultural cues and labels such as terrorism.
Levels of gender bias uncovered within CLIP for different regions aligned with global indices of societal gender equality, with those from the Global South reflecting the highest levels of gender bias.
BIAS 2023: Advances in Bias and Fairness in Information Retrieval. Communications in Computer and Information Science (CCIS)
1840.
CEUR-WS. ISBN 978-3-031-37248-3
e <A+> Alliance / Women at the Table as an Inaugural Tech Fellow 2020/2021, Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289_2, European Regional Development Fund
ID Code:
29035
Deposited On:
15 Sep 2023 12:04 by
Abhishek Mandal
. Last Modified 15 Sep 2023 12:04