A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Hugo Berg, Siobhan Hall, Yash Bhalgat, Hannah Kirk, Aleksandar Shtedritski, Max Bain
Abstract
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we investigate bias measures and apply ranking metrics for image-text representations. We then investigate debiasing methods and show that prepending learned embeddings to text queries that are jointly trained with adversarial debiasing and a contrastive loss, reduces various bias measures with minimal degradation to the image-text representation.- Anthology ID:
- 2022.aacl-main.61
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 806–822
- Language:
- URL:
- https://aclanthology.org/2022.aacl-main.61
- DOI:
- Cite (ACL):
- Hugo Berg, Siobhan Hall, Yash Bhalgat, Hannah Kirk, Aleksandar Shtedritski, and Max Bain. 2022. A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 806–822, Online only. Association for Computational Linguistics.
- Cite (Informal):
- A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning (Berg et al., AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.aacl-main.61.pdf