# Contextualizing Hate Speech Classifiers with Post-hoc Explanation

arXiv: https://arxiv.org/abs/2005.02439 · HTML: https://mlsanity.com/paper/2005.02439/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 30 of 84)

- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (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)
- [Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists](https://mlsanity.com/paper/2203.09192/) (2022)
- [Nationality Bias in Text Generation](https://mlsanity.com/paper/2302.02463/) (2023)
- [SemEval-2023 Task 10: Explainable Detection of Online Sexism](https://mlsanity.com/paper/2303.04222/) (2023)
- [HateMM: A Multi-Modal Dataset for Hate Video Classification](https://mlsanity.com/paper/2305.03915/) (2023)
- [On Explaining Multimodal Hateful Meme Detection Models](https://mlsanity.com/paper/2204.01734/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [An Empirical Study on Explanations in Out-of-Domain Settings](https://mlsanity.com/paper/2203.00056/) (2022)
- [Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models](https://mlsanity.com/paper/2206.03945/) (2022)
- [Fairness-aware Class Imbalanced Learning](https://mlsanity.com/paper/2109.10444/) (2021)
- [Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework](https://mlsanity.com/paper/2109.13137/) (2021)
- [Detecting Community Sensitive Norm Violations in Online Conversations](https://mlsanity.com/paper/2110.04419/) (2021)
- [Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience](https://mlsanity.com/paper/2108.13759/) (2021)
- [Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles](https://mlsanity.com/paper/2308.04346/) (2023)
- [KOLD: Korean Offensive Language Dataset](https://mlsanity.com/paper/2205.11315/) (2022)
- [Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech](https://mlsanity.com/paper/2109.00591/) (2021)
- [Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models](https://mlsanity.com/paper/2111.13259/) (2021)
- [Hate Speech Classifiers Learn Human-Like Social Stereotypes](https://mlsanity.com/paper/2110.14839/) (2021)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection](https://mlsanity.com/paper/2205.04238/) (2022)
- [Explainable Abuse Detection as Intent Classification and Slot Filling](https://mlsanity.com/paper/2210.02659/) (2022)
- [Should We Attend More or Less? Modulating Attention for Fairness](https://mlsanity.com/paper/2305.13088/) (2023)
- [Improving Counterfactual Generation for Fair Hate Speech Detection](https://mlsanity.com/paper/2108.01721/) (2021)

## Abstract (arXiv)

Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways. Such biases manifest in false positives when these identifiers are present, due to models' inability to learn the contexts which constitute a hateful usage of identifiers. We extract SOC post-hoc explanations from fine-tuned BERT classifiers to efficiently detect bias towards identity terms. Then, we propose a novel regularization technique based on these explanations that encourages models to learn from the context of group identifiers in addition to the identifiers themselves. Our approach improved over baselines in limiting false positives on out-of-domain data while maintaining or improving in-domain performance. Project page: https://inklab.usc.edu/contextualize-hate-speech/.