BiasDora: Exploring Hidden Biased Associations in Vision-Language Models

Autor:	Raj, Chahat, Mukherjee, Anjishnu, Caliskan, Aylin, Anastasopoulos, Antonios, Zhu, Ziwei
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the Dataset of retrieved associations, (Dora), publicly available here https://github.com/chahatraj/BiasDora. Comment: Accepted to EMNLP Findings 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.02066 Zobrazit plný text záznamu View this record from Arxiv