Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models

Laura Cabello, Emanuele Bugliarello, Stephanie Brandl, Desmond Elliott


Abstract
Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind those prejudicial biases to ensure that model performance does not result in discriminatory behaviour toward certain groups or populations. In this work, we define gender bias as our case study. We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models. We investigate the connection, if any, between the two learning stages, and evaluate how bias amplification reflects on model performance. Overall, we find that bias amplification in pretraining and after fine-tuning are independent. We then examine the effect of continued pretraining on gender-neutral data, finding that this reduces group disparities, i.e., promotes fairness, on VQAv2 and retrieval tasks without significantly compromising task performance.
Anthology ID:
2023.emnlp-main.525
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8465–8483
Language:
URL:
https://aclanthology.org/2023.emnlp-main.525
DOI:
10.18653/v1/2023.emnlp-main.525
Bibkey:
Cite (ACL):
Laura Cabello, Emanuele Bugliarello, Stephanie Brandl, and Desmond Elliott. 2023. Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8465–8483, Singapore. Association for Computational Linguistics.
Cite (Informal):
Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models (Cabello et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.emnlp-main.525.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.emnlp-main.525.mp4