# Toward Understanding Bias Correlations for Mitigation in NLP

arXiv: https://arxiv.org/abs/2205.12391 · HTML: https://mlsanity.com/paper/2205.12391/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Evaluating the Underlying Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.08783/) (2019)
- [Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model](https://mlsanity.com/paper/2008.06460/) (2020)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Gender-preserving Debiasing for Pre-trained Word Embeddings](https://mlsanity.com/paper/1906.00742/) (2019)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting](https://mlsanity.com/paper/2004.14088/) (2020)
- [Investigating Gender Bias in BERT](https://mlsanity.com/paper/2009.05021/) (2020)
- [Intersectional Bias in Hate Speech and Abusive Language Datasets](https://mlsanity.com/paper/2005.05921/) (2020)
- [Debiasing Embeddings for Reduced Gender Bias in Text Classification](https://mlsanity.com/paper/1908.02810/) (2019)
- [Cyberbullying Detection with Fairness Constraints](https://mlsanity.com/paper/2005.06625/) (2020)
- [Native Language Cognate Effects on Second Language Lexical Choice](https://mlsanity.com/paper/1805.09590/) (2018)
- [Empirical Analysis of Multi-Task Learning for Reducing Model Bias in Toxic Comment Detection](https://mlsanity.com/paper/1909.09758/) (2019)

## Built on by (most cited first, 5 of 5)

- [Language Models Predict Empathy Gaps Between Social In-groups and Out-groups](https://mlsanity.com/paper/2503.01030/) (2025)
- [Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis](https://mlsanity.com/paper/2310.00347/) (2023)
- [A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier](https://mlsanity.com/paper/2310.12785/) (2023)
- [Debiasing Word Embeddings with Nonlinear Geometry](https://mlsanity.com/paper/2208.13899/) (2022)
- [Controllable Pareto Trade-off between Fairness and Accuracy](https://mlsanity.com/paper/2509.13651/) (2025)

## Abstract (arXiv)

Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with unprecedented effort and proposed promising approaches for bias mitigation. In spite of considerable practical importance, current algorithmic fairness literature lacks an in-depth understanding of the relations between different forms of biases. Social bias is complex by nature. Numerous studies in social psychology identify the "generalized prejudice", i.e., generalized devaluing sentiments across different groups. For example, people who devalue ethnic minorities are also likely to devalue women and gays. Therefore, this work aims to provide a first systematic study toward understanding bias correlations in mitigation. In particular, we examine bias mitigation in two common NLP tasks -- toxicity detection and word embeddings -- on three social identities, i.e., race, gender, and religion. Our findings suggest that biases are correlated and present scenarios in which independent debiasing approaches dominant in current literature may be insufficient. We further investigate whether jointly mitigating correlated biases is more desired than independent and individual debiasing. Lastly, we shed light on the inherent issue of debiasing-accuracy trade-off in bias mitigation. This study serves to motivate future research on joint bias mitigation that accounts for correlated biases.