# Incorporating Human Explanations for Robust Hate Speech Detection

arXiv: https://arxiv.org/abs/2411.06213 · HTML: https://mlsanity.com/paper/2411.06213/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 9 Nov 2024.

## Builds on (most cited first, 6 of 6)

- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Did the Model Understand the Question?](https://mlsanity.com/paper/1805.05492/) (2018)
- [Spread of hate speech in online social media](https://mlsanity.com/paper/1812.01693/) (2018)
- [Challenges in Discriminating Profanity from Hate Speech](https://mlsanity.com/paper/1803.05495/) (2018)
- [The Effect of Extremist Violence on Hateful Speech Online](https://mlsanity.com/paper/1804.05704/) (2018)
- [Detecting and Reducing Bias in a High Stakes Domain](https://mlsanity.com/paper/1908.11474/) (2019)

## Abstract (arXiv)

Given the black-box nature and complexity of large transformer language models (LM), concerns about generalizability and robustness present ethical implications for domains such as hate speech (HS) detection. Using the content rich Social Bias Frames dataset, containing human-annotated stereotypes, intent, and targeted groups, we develop a three stage analysis to evaluate if LMs faithfully assess hate speech. First, we observe the need for modeling contextually grounded stereotype intents to capture implicit semantic meaning. Next, we design a new task, Stereotype Intent Entailment (SIE), which encourages a model to contextually understand stereotype presence. Finally, through ablation tests and user studies, we find a SIE objective improves content understanding, but challenges remain in modeling implicit intent.