# HateDebias: On the Diversity and Variability of Hate Speech Debiasing

arXiv: https://arxiv.org/abs/2406.04876 · HTML: https://mlsanity.com/paper/2406.04876/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 68 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Builds on (most cited first, 30 of 49)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [Continual Learning for Text Classification with Information Disentanglement Based Regularization](https://mlsanity.com/paper/2104.05489/) (2021)
- [Learning and Evaluating General Linguistic Intelligence](https://mlsanity.com/paper/1901.11373/) (2019)
- [Sentence Embedding Alignment for Lifelong Relation Extraction](https://mlsanity.com/paper/1903.02588/) (2019)
- [ETHOS: an Online Hate Speech Detection Dataset](https://mlsanity.com/paper/2006.08328/) (2020)
- [Essentials for Class Incremental Learning](https://mlsanity.com/paper/2102.09517/) (2021)
- [Subspace Regularizers for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2110.07059/) (2021)
- [Fairness-guided Few-shot Prompting for Large Language Models](https://mlsanity.com/paper/2303.13217/) (2023)
- [Probing LLMs for hate speech detection: strengths and vulnerabilities](https://mlsanity.com/paper/2310.12860/) (2023)
- [Layerwise Optimization by Gradient Decomposition for Continual Learning](https://mlsanity.com/paper/2105.07561/) (2021)
- [Diverse Adversaries for Mitigating Bias in Training](https://mlsanity.com/paper/2101.10001/) (2021)

## Abstract (arXiv)

Hate speech frequently appears on social media platforms and urgently needs to be effectively controlled. Alleviating the bias caused by hate speech can help resolve various ethical issues. Although existing research has constructed several datasets for hate speech detection, these datasets seldom consider the diversity and variability of bias, making them far from real-world scenarios. To fill this gap, we propose a benchmark HateDebias to analyze the fairness of models under dynamically evolving environments. Specifically, to meet the diversity of biases, we collect hate speech data with different types of biases from real-world scenarios. To further simulate the variability in the real-world scenarios(i.e., the changing of bias attributes in datasets), we construct a dataset to follow the continuous learning setting and evaluate the detection accuracy of models on the HateDebias, where performance degradation indicates a significant bias toward a specific attribute. To provide a potential direction, we further propose a continual debiasing framework tailored to dynamic bias in real-world scenarios, integrating memory replay and bias information regularization to ensure the fairness of the model. Experiment results on the HateDebias benchmark reveal that our methods achieve improved performance in mitigating dynamic biases in real-world scenarios, highlighting the practicality in real-world applications.