# Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework

arXiv: https://arxiv.org/abs/2109.13137 · HTML: https://mlsanity.com/paper/2109.13137/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 27 Sep 2021.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Toward a better trade-off between performance and fairness with kernel-based distribution matching](https://mlsanity.com/paper/1910.11779/) (2019)
- [Examining a hate speech corpus for hate speech detection and popularity prediction](https://mlsanity.com/paper/1805.04661/) (2018)
- [On Analyzing Annotation Consistency in Online Abusive Behavior Datasets](https://mlsanity.com/paper/2006.13507/) (2020)

## Built on by (most cited first, 19 of 19)

- [Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation](https://mlsanity.com/paper/2205.00501/) (2022)
- [Multi-VALUE: A Framework for Cross-Dialectal English NLP](https://mlsanity.com/paper/2212.08011/) (2022)
- [VALUE: Understanding Dialect Disparity in NLU](https://mlsanity.com/paper/2204.03031/) (2022)
- [A Material Lens on Coloniality in NLP](https://mlsanity.com/paper/2311.08391/) (2023)
- [NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps](https://mlsanity.com/paper/2404.01651/) (2024)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [Watch Your Language: Investigating Content Moderation with Large Language Models](https://mlsanity.com/paper/2309.14517/) (2023)
- [DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules](https://mlsanity.com/paper/2305.13406/) (2023)
- ["Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People](https://mlsanity.com/paper/2410.03448/) (2024)
- [Task-Agnostic Low-Rank Adapters for Unseen English Dialects](https://mlsanity.com/paper/2311.00915/) (2023)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English](https://mlsanity.com/paper/2206.08978/) (2022)
- [Data Caricatures: On the Representation of African American Language in Pretraining Corpora](https://mlsanity.com/paper/2503.10789/) (2025)
- [A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter](https://mlsanity.com/paper/2210.06351/) (2022)
- [Centering the Margins: Outlier-Based Identification of Harmed Populations in Toxicity Detection](https://mlsanity.com/paper/2305.14735/) (2023)
- [Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness](https://mlsanity.com/paper/2406.09977/) (2024)
- [NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers](https://mlsanity.com/paper/2407.01697/) (2024)
- [Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models](https://mlsanity.com/paper/2606.07522/) (2026)

## Abstract (arXiv)

Recent research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to use additional descriptive fairness metrics to better understand the source of these biases. We demonstrate that different benchmark classifiers, as well as two in-process bias-remediation techniques, propagate racial biases even in a larger corpus. We then propose a novel ensemble-framework that uses a specialized classifier that is fine-tuned to the African American English dialect. We show that our proposed framework substantially reduces the racial biases that the model learns from these datasets. We demonstrate how the ensemble framework improves fairness metrics across all sample datasets with minimal impact on the classification performance, and provide empirical evidence in its ability to unlearn the annotation biases towards authors who use African American English. ** Please note that this work may contain examples of offensive words and phrases.