# Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection

arXiv: https://arxiv.org/abs/2511.07065 · HTML: https://mlsanity.com/paper/2511.07065/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 10 Nov 2025.

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

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [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)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1609.01454/) (2016)
- [Learning to Faithfully Rationalize by Construction](https://mlsanity.com/paper/2005.00115/) (2020)
- [Inferring Which Medical Treatments Work from Reports of Clinical Trials](https://mlsanity.com/paper/1904.01606/) (2019)
- [Do Human Rationales Improve Machine Explanations?](https://mlsanity.com/paper/1905.13714/) (2019)
- [HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning](https://mlsanity.com/paper/2311.00321/) (2023)
- [Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales](https://mlsanity.com/paper/2403.12403/) (2024)
- [Multilingual and Explainable Text Detoxification with Parallel Corpora](https://mlsanity.com/paper/2412.11691/) (2024)
- [IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models](https://mlsanity.com/paper/2303.03124/) (2023)

## Built on by (most cited first, 3 of 3)

- [Self-Explaining Hate Speech Detection with Moral Rationales](https://mlsanity.com/paper/2601.03481/) (2026)
- [TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction](https://mlsanity.com/paper/2602.11700/) (2026)
- [Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection](https://mlsanity.com/paper/2605.31563/) (2026)

## Abstract (arXiv)

The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a framework that explicitly aligns model attention with human rationales, improving both interpretability and fairness in hate speech classification. SRA integrates a supervised attention mechanism into transformer-based classifiers, optimizing a joint objective that combines standard classification loss with an alignment loss term that minimizes the discrepancy between attention weights and human-annotated rationales. We evaluated SRA on hate speech benchmarks in English (HateXplain) and Portuguese (HateBRXplain) with rationale annotations. Empirically, SRA achieves 2.4x better explainability compared to current baselines, and produces token-level explanations that are more faithful and human-aligned. In terms of fairness, SRA achieves competitive fairness across all measures, with second-best performance in detecting toxic posts targeting identity groups, while maintaining comparable results on other metrics. These findings demonstrate that incorporating human rationales into attention mechanisms can enhance interpretability and faithfulness without compromising fairness.