Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models
Abstract
Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for debiasing, which are resource-intensive and costly. Furthermore, these methods hurt the PLMs' performance on downstream tasks. In this study, we propose Gender-tuning, which debiases the PLMs through fine-tuning on downstream tasks' datasets. For this aim, Gender-tuning integrates Masked Language Modeling (MLM) training objectives into fine-tuning's training process. Comprehensive experiments show that Gender-tuning outperforms the state-of-the-art baselines in terms of average gender bias scores in PLMs while improving PLMs' performance on downstream tasks solely using the downstream tasks' dataset. Also, Gender-tuning is a deployable debiasing tool for any PLM that works with original fine-tuning.
Keywords
Cite
@article{arxiv.2307.10522,
title = {Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models},
author = {Somayeh Ghanbarzadeh and Yan Huang and Hamid Palangi and Radames Cruz Moreno and Hamed Khanpour},
journal= {arXiv preprint arXiv:2307.10522},
year = {2023}
}