An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper. The current techniques used to measure and debias PLMs are skewed towards the US racial biases and rely on pre-defined bias attributes (e.g. "black" vs "white"). Some require large datasets and further pre-training. Such techniques are not designed to capture the underrepresented indigenous populations in other countries, such as M\=aori in New Zealand. Local knowledge and understanding must be incorporated to ensure unbiased algorithms, especially when addressing a resource-restricted society.
@article{arxiv.2304.11094,
title = {Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis},
author = {Vithya Yogarajan and Gillian Dobbie and Henry Gouk},
journal= {arXiv preprint arXiv:2304.11094},
year = {2023}
}