# Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales

arXiv: https://arxiv.org/abs/2608.26125 · HTML: https://mlsanity.com/paper/2608.26125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [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)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [Training Classifiers with Natural Language Explanations](https://mlsanity.com/paper/1805.03818/) (2018)
- [Disembodied Machine Learning: On the Illusion of Objectivity in NLP](https://mlsanity.com/paper/2101.11974/) (2021)
- [What to Learn, and How: Toward Effective Learning from Rationales](https://mlsanity.com/paper/2112.00071/) (2021)
- [Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection](https://mlsanity.com/paper/2205.04238/) (2022)
- [HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection](https://mlsanity.com/paper/2008.09820/) (2020)

## Abstract (arXiv)

Online hate against Muslim communities often appears in culturally coded, multilingual forms that evade conventional AI moderation. Such systems, though accurate, remain opaque and risk bias, over-censorship, or under-moderation, particularly when detached from sociocultural context. We propose a training-time explainability framework that aligns model reasoning with human-annotated rationales, improving both classification performance and interpretability. Our approach is evaluated on HateXplain (English) and BullySent (Hinglish), reflecting the prevalence of anti-Muslim hate across both languages. Using LIME, Integrated Gradients, Grad X Input, and attention, we assess accuracy, explanation quality, and cross-method agreement. Results show that gradient- and attention-based regularization improve F-scores, enhance plausibility and faithfulness, and capture culturally specific cues for detecting implicit anti-Muslim hate, offering a path toward multilingual, culturally aware content moderation.