How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification

by   Ewoenam Tokpo, et al.

To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text classification, it is important to understand how these intrinsic bias mitigation strategies actually translate to fairness in downstream tasks and the extent of this. In this work, we design a probe to investigate the effects that some of the major intrinsic gender bias mitigation strategies have on downstream text classification tasks. We discover that instead of resolving gender bias, intrinsic mitigation techniques and metrics are able to hide it in such a way that significant gender information is retained in the embeddings. Furthermore, we show that each mitigation technique is able to hide the bias from some of the intrinsic bias measures but not all, and each intrinsic bias measure can be fooled by some mitigation techniques, but not all. We confirm experimentally, that none of the intrinsic mitigation techniques used without any other fairness intervention is able to consistently impact extrinsic bias. We recommend that intrinsic bias mitigation techniques should be combined with other fairness interventions for downstream tasks.


page 15

page 16


Debiasing Embeddings for Reduced Gender Bias in Text Classification

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings ca...

Parameter-efficient Modularised Bias Mitigation via AdapterFusion

Large pre-trained language models contain societal biases and carry alon...

Bias mitigation techniques in image classification: fair machine learning in human heritage collections

A major problem with using automated classification systems is that if t...

Challenges in Detoxifying Language Models

Large language models (LM) generate remarkably fluent text and can be ef...

MABEL: Attenuating Gender Bias using Textual Entailment Data

Pre-trained language models encode undesirable social biases, which are ...

Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification

Existing bias mitigation methods to reduce disparities in model outcomes...

On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations

Multiple metrics have been introduced to measure fairness in various nat...

Please sign up or login with your details

Forgot password? Click here to reset