# Demoting Racial Bias in Hate Speech Detection

arXiv: https://arxiv.org/abs/2005.12246 · HTML: https://mlsanity.com/paper/2005.12246/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 30 of 62)

- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [A Survey of Race, Racism, and Anti-Racism in NLP](https://mlsanity.com/paper/2106.11410/) (2021)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities](https://mlsanity.com/paper/2102.04257/) (2021)
- [Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering](https://mlsanity.com/paper/2211.03433/) (2022)
- [Evaluation of African American Language Bias in Natural Language Generation](https://mlsanity.com/paper/2305.14291/) (2023)
- [Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study](https://mlsanity.com/paper/2204.01440/) (2022)
- [Modeling the Second Player in Distributionally Robust Optimization](https://mlsanity.com/paper/2103.10282/) (2021)
- [On Explaining Multimodal Hateful Meme Detection Models](https://mlsanity.com/paper/2204.01734/) (2022)
- [An Information-theoretic Approach to Distribution Shifts](https://mlsanity.com/paper/2106.03783/) (2021)
- [Parameter-efficient Modularised Bias Mitigation via AdapterFusion](https://mlsanity.com/paper/2302.06321/) (2023)
- [What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection](https://mlsanity.com/paper/2402.00371/) (2024)
- [Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework](https://mlsanity.com/paper/2109.13137/) (2021)
- [Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks](https://mlsanity.com/paper/2205.15171/) (2022)
- [Controlling Bias Exposure for Fair Interpretable Predictions](https://mlsanity.com/paper/2210.07455/) (2022)
- [Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations](https://mlsanity.com/paper/2503.01623/) (2025)
- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [Hate Speech Classifiers Learn Human-Like Social Stereotypes](https://mlsanity.com/paper/2110.14839/) (2021)
- [Detecting Unintended Social Bias in Toxic Language Datasets](https://mlsanity.com/paper/2210.11762/) (2022)
- [ToxCCIn: Toxic Content Classification with Interpretability](https://mlsanity.com/paper/2103.01328/) (2021)
- [BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla](https://mlsanity.com/paper/2410.13281/) (2024)
- [From Toxicity in Online Comments to Incivility in American News: Proceed with Caution](https://mlsanity.com/paper/2102.03671/) (2021)
- [Automated Identification of Toxic Code Reviews Using ToxiCR](https://mlsanity.com/paper/2202.13056/) (2022)
- [Mitigating Gender Bias in Machine Translation through Adversarial Learning](https://mlsanity.com/paper/2203.10675/) (2022)

## Abstract (arXiv)

In current hate speech datasets, there exists a high correlation between annotators' perceptions of toxicity and signals of African American English (AAE). This bias in annotated training data and the tendency of machine learning models to amplify it cause AAE text to often be mislabeled as abusive/offensive/hate speech with a high false positive rate by current hate speech classifiers. In this paper, we use adversarial training to mitigate this bias, introducing a hate speech classifier that learns to detect toxic sentences while demoting confounds corresponding to AAE texts. Experimental results on a hate speech dataset and an AAE dataset suggest that our method is able to substantially reduce the false positive rate for AAE text while only minimally affecting the performance of hate speech classification.