Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Gender bias in multimodal models a transnational feminist approach considering geographical region and culture

Mandal, Abhishek orcid logoORCID: 0000-0002-5275-4192, Little, Suzanne orcid logoORCID: 0000-0003-3281-3471 and Leavy, Susan orcid logoORCID: 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

Abstract
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.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Bias; Multimodal Models; Generative Models
Subjects:Computer Science > Artificial intelligence
Social Sciences > Gender
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: 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
Publisher:CEUR-WS
Official URL:https://doi.org/10.1007/978-3-031-37249-0_2
Copyright Information:© 2023 The Authors.
Funders: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
Documents

Full text available as:

[thumbnail of Gender Bias in Multimodal Models - A Transnational Feminist Approach Considering Geographical Region and Culture.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0
8MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record