# Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster

arXiv: https://arxiv.org/abs/2406.04106 · HTML: https://mlsanity.com/paper/2406.04106/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 13 of 13)

- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [SemEval-2023 Task 10: Explainable Detection of Online Sexism](https://mlsanity.com/paper/2303.04222/) (2023)
- [Evaluating GPT-3 Generated Explanations for Hateful Content Moderation](https://mlsanity.com/paper/2305.17680/) (2023)
- [Tackling Online Abuse: A Survey of Automated Abuse Detection Methods](https://mlsanity.com/paper/1908.06024/) (2019)
- [Explainable Abuse Detection as Intent Classification and Slot Filling](https://mlsanity.com/paper/2210.02659/) (2022)
- [Cross-Policy Compliance Detection via Question Answering](https://mlsanity.com/paper/2109.03731/) (2021)
- [Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators](https://mlsanity.com/paper/2310.15055/) (2023)

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

- [ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection](https://mlsanity.com/paper/2510.08630/) (2025)
- [Compositional Generalisation for Explainable Hate Speech Detection](https://mlsanity.com/paper/2506.03916/) (2025)
- [The Enforcement and Feasibility of Hate Speech Moderation](https://mlsanity.com/paper/2604.12289/) (2026)
- [SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models](https://mlsanity.com/paper/2509.15174/) (2025)
- [HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations](https://mlsanity.com/paper/2601.13547/) (2026)
- [Hate Speech Detection in Turkish and Arabic: A Comprehensive Study](https://mlsanity.com/paper/2607.00143/) (2026)
- [Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization](https://mlsanity.com/paper/2610.02019/) (2026)

## Abstract (arXiv)

Content moderators play a key role in keeping the conversation on social media healthy. While the high volume of content they need to judge represents a bottleneck to the moderation pipeline, no studies have explored how models could support them to make faster decisions. There is, by now, a vast body of research into detecting hate speech, sometimes explicitly motivated by a desire to help improve content moderation, but published research using real content moderators is scarce. In this work we investigate the effect of explanations on the speed of real-world moderators. Our experiments show that while generic explanations do not affect their speed and are often ignored, structured explanations lower moderators' decision making time by 7.4%.