Debiasing Isn’t Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks
Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki
Abstract
We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for MLMs, and find that there exists only a weak correlation between these two types of evaluation measures. Moreover, we find that MLMs debiased using different methods still re-learn social biases during fine-tuning on downstream tasks. We identify the social biases in both training instances as well as their assigned labels as reasons for the discrepancy between intrinsic and extrinsic bias evaluation measurements. Overall, our findings highlight the limitations of existing MLM bias evaluation measures and raise concerns on the deployment of MLMs in downstream applications using those measures.
BibTeX
@inproceedings{kaneko-etal-2022-debiasing,
title = "Debiasing Isn{'}t Enough! {--} on the Effectiveness of Debiasing {MLM}s and Their Social Biases in Downstream Tasks",
author = "Kaneko, Masahiro and
Bollegala, Danushka and
Okazaki, Naoaki",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.111/",
pages = "1299--1310"
}