BiasDora: Exploring Hidden Biased Associations in Vision-Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910631875051520 |
|---|---|
| author | Raj, Chahat Mukherjee, Anjishnu Caliskan, Aylin Anastasopoulos, Antonios Zhu, Ziwei |
| author_facet | Raj, Chahat Mukherjee, Anjishnu Caliskan, Aylin Anastasopoulos, Antonios Zhu, Ziwei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02066 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BiasDora: Exploring Hidden Biased Associations in Vision-Language Models Raj, Chahat Mukherjee, Anjishnu Caliskan, Aylin Anastasopoulos, Antonios Zhu, Ziwei Computation and Language 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. |
| title | BiasDora: Exploring Hidden Biased Associations in Vision-Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.02066 |