# Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI

arXiv: https://arxiv.org/abs/2407.20274 · HTML: https://mlsanity.com/paper/2407.20274/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [Thou shalt not hate: Countering Online Hate Speech](https://mlsanity.com/paper/1808.04409/) (2018)
- [GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers](https://mlsanity.com/paper/2205.03286/) (2022)
- [Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisis](https://mlsanity.com/paper/2005.12423/) (2020)
- [Metrics for saliency map evaluation of deep learning explanation methods](https://mlsanity.com/paper/2201.13291/) (2022)
- [Hate Speech and Counter Speech Detection: Conversational Context Does Matter](https://mlsanity.com/paper/2206.06423/) (2022)
- [Countering hate on social media: Large scale classification of hate and counter speech](https://mlsanity.com/paper/2006.01974/) (2020)
- [Analyzing the hate and counter speech accounts on Twitter](https://mlsanity.com/paper/1812.02712/) (2018)
- [On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification](https://mlsanity.com/paper/2101.00196/) (2021)
- [ProtoTEx: Explaining Model Decisions with Prototype Tensors](https://mlsanity.com/paper/2204.05426/) (2022)
- [On the Explanation of Machine Learning Predictions in Clinical Gait Analysis](https://mlsanity.com/paper/1912.07737/) (2019)
- [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](https://mlsanity.com/paper/2212.07425/) (2022)
- [Hate Cannot Drive out Hate: Forecasting Conversation Incivility following Replies to Hate Speech](https://mlsanity.com/paper/2312.04804/) (2023)
- [ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls](https://mlsanity.com/paper/2208.00176/) (2022)

## Built on by (most cited first, 1 of 1)

- [Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition](https://mlsanity.com/paper/2508.08274/) (2025)

## Abstract (arXiv)

In this paper we investigate the explainability of transformer models and their plausibility for hate speech and counter speech detection. We compare representatives of four different explainability approaches, i.e., gradient-based, perturbation-based, attention-based, and prototype-based approaches, and analyze them quantitatively with an ablation study and qualitatively in a user study. Results show that perturbation-based explainability performs best, followed by gradient-based and attention-based explainability. Prototypebased experiments did not yield useful results. Overall, we observe that explainability strongly supports the users in better understanding the model predictions.