# Power of Explanations: Towards automatic debiasing in hate speech detection

arXiv: https://arxiv.org/abs/2209.09975 · HTML: https://mlsanity.com/paper/2209.09975/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 7 Sep 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Mitigating Language-Dependent Ethnic Bias in BERT](https://mlsanity.com/paper/2109.05704/) (2021)
- [Semi-supervised sequence tagging with bidirectional language models](https://mlsanity.com/paper/1705.00108/) (2017)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [A Survey on Text Classification: From Shallow to Deep Learning](https://mlsanity.com/paper/2008.00364/) (2020)
- [AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models](https://mlsanity.com/paper/1909.09251/) (2019)
- [Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs](https://mlsanity.com/paper/1801.05453/) (2018)
- [Randomness In Neural Network Training: Characterizing The Impact of Tooling](https://mlsanity.com/paper/2106.11872/) (2021)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [AdaFair: Cumulative Fairness Adaptive Boosting](https://mlsanity.com/paper/1909.08982/) (2019)
- [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)
- [FAE: A Fairness-Aware Ensemble Framework](https://mlsanity.com/paper/2002.00695/) (2020)
- [Explain and Predict, and then Predict Again](https://mlsanity.com/paper/2101.04109/) (2021)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [Consequence-aware Sequential Counterfactual Generation](https://mlsanity.com/paper/2104.05592/) (2021)
- [How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection](https://mlsanity.com/paper/1902.10339/) (2019)
- [XPROAX-Local explanations for text classification with progressive neighborhood approximation](https://mlsanity.com/paper/2109.15004/) (2021)

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

- [NBIAS: A Natural Language Processing Framework for Bias Identification in Text](https://mlsanity.com/paper/2308.01681/) (2023)
- [Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis](https://mlsanity.com/paper/2310.00347/) (2023)
- [Exploring Fusion Techniques in Multimodal AI-Based Recruitment: Insights from FairCVdb](https://mlsanity.com/paper/2407.16892/) (2024)
- [Explaining text classifiers through progressive neighborhood approximation with realistic samples](https://mlsanity.com/paper/2302.07733/) (2023)
- [A Multifaceted Analysis of Social Biases in Large Language Models](https://mlsanity.com/paper/2512.15792/) (2025)

## Abstract (arXiv)

Hate speech detection is a common downstream application of natural language processing (NLP) in the real world. In spite of the increasing accuracy, current data-driven approaches could easily learn biases from the imbalanced data distributions originating from humans. The deployment of biased models could further enhance the existing social biases. But unlike handling tabular data, defining and mitigating biases in text classifiers, which deal with unstructured data, are more challenging. A popular solution for improving machine learning fairness in NLP is to conduct the debiasing process with a list of potentially discriminated words given by human annotators. In addition to suffering from the risks of overlooking the biased terms, exhaustively identifying bias with human annotators are unsustainable since discrimination is variable among different datasets and may evolve over time. To this end, we propose an automatic misuse detector (MiD) relying on an explanation method for detecting potential bias. And built upon that, an end-to-end debiasing framework with the proposed staged correction is designed for text classifiers without any external resources required.