# Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models

arXiv: https://arxiv.org/abs/2110.01094 · HTML: https://mlsanity.com/paper/2110.01094/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 3 Oct 2021.

## Builds on (most cited first, 16 of 16)

- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [Adversarial Training for Large Neural Language Models](https://mlsanity.com/paper/2004.08994/) (2020)
- [Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem](https://mlsanity.com/paper/2004.04498/) (2020)
- [Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00699/) (2020)
- [Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation](https://mlsanity.com/paper/2005.00965/) (2020)

## Built on by (most cited first, 1 of 1)

- [Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias](https://mlsanity.com/paper/2204.10365/) (2022)

## Abstract (arXiv)

Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples generation and evaluation for conducting data augmentation or adversarial learning. In the meanwhile, gender bias embedded in the models seems to be a serious problem in practical applications. Many researches have covered the gender bias produced by word-level information(e.g. gender-stereotypical occupations), while few researchers have investigated the sentence-level cases and implicit cases. In this paper, we proposed a method to automatically generate implicit gender bias samples at sentence-level and a metric to measure gender bias. Samples generated by our method will be evaluated in terms of accuracy. The metric will be used to guide the generation of examples from Pre-trained models. Therefore, those examples could be used to impose attacks on Pre-trained Models. Finally, we discussed the evaluation efficacy of our generated examples on reducing gender bias for future research.