Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis. (arXiv:2304.11094v1 [cs.CL])

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 …

algorithms analysis arxiv bias biases datasets knowledge language language models large datasets new zealand paper perspective pre-training society training unbiased understanding