# Why Is It Hate Speech? Masked Rationale Prediction for Explainable Hate Speech Detection

arXiv: https://arxiv.org/abs/2211.00243 · HTML: https://mlsanity.com/paper/2211.00243/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 1 Nov 2022.

## Builds on (most cited first, 18 of 18)

- [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)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks](https://mlsanity.com/paper/1811.01088/) (2018)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Muppet: Massive Multi-task Representations with Pre-Finetuning](https://mlsanity.com/paper/2101.11038/) (2021)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Training Classifiers with Natural Language Explanations](https://mlsanity.com/paper/1805.03818/) (2018)
- [Towards Explainable NLP: A Generative Explanation Framework for Text Classification](https://mlsanity.com/paper/1811.00196/) (2018)
- [Deriving Machine Attention from Human Rationales](https://mlsanity.com/paper/1808.09367/) (2018)
- [PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models](https://mlsanity.com/paper/2006.09075/) (2020)
- [Predictive Embeddings for Hate Speech Detection on Twitter](https://mlsanity.com/paper/1809.10644/) (2018)

## Built on by (most cited first, 7 of 7)

- [SemEval-2023 Task 10: Explainable Detection of Online Sexism](https://mlsanity.com/paper/2303.04222/) (2023)
- [Detecting and Correcting Hate Speech in Multimodal Memes with Large Visual Language Model](https://mlsanity.com/paper/2311.06737/) (2023)
- [Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality](https://mlsanity.com/paper/2305.10547/) (2023)
- [A survey of textual cyber abuse detection using cutting-edge language models and large language models](https://mlsanity.com/paper/2501.05443/) (2025)
- [Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models](https://mlsanity.com/paper/2505.00150/) (2025)
- [ContextIQ: A Multimodal Expert-Based Video Retrieval System for Contextual Advertising](https://mlsanity.com/paper/2410.22233/) (2024)
- [Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?](https://mlsanity.com/paper/2509.22291/) (2025)

## Abstract (arXiv)

In a hate speech detection model, we should consider two critical aspects in addition to detection performance-bias and explainability. Hate speech cannot be identified based solely on the presence of specific words: the model should be able to reason like humans and be explainable. To improve the performance concerning the two aspects, we propose Masked Rationale Prediction (MRP) as an intermediate task. MRP is a task to predict the masked human rationales-snippets of a sentence that are grounds for human judgment-by referring to surrounding tokens combined with their unmasked rationales. As the model learns its reasoning ability based on rationales by MRP, it performs hate speech detection robustly in terms of bias and explainability. The proposed method generally achieves state-of-the-art performance in various metrics, demonstrating its effectiveness for hate speech detection.