# Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language

arXiv: https://arxiv.org/abs/2402.13818 · HTML: https://mlsanity.com/paper/2402.13818/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Builds on (most cited first, 5 of 5)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [A Framework for the Computational Linguistic Analysis of Dehumanization](https://mlsanity.com/paper/2003.03014/) (2020)
- ["It's Not Just Hate'': A Multi-Dimensional Perspective on Detecting Harmful Speech Online](https://mlsanity.com/paper/2210.15870/) (2022)
- [A Dataset for the Detection of Dehumanizing Language](https://mlsanity.com/paper/2402.08764/) (2024)

## Built on by (most cited first, 2 of 2)

- [Beyond the Explicit: A Bilingual Dataset for Dehumanization Detection in Social Media](https://mlsanity.com/paper/2510.18582/) (2025)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)

## Abstract (arXiv)

Dehumanization, i.e., denying human qualities to individuals or groups, is a particularly harmful form of hate speech that can normalize violence against marginalized communities. Despite advances in NLP for detecting general hate speech, approaches to identifying dehumanizing language remain limited due to scarce annotated data and the subtle nature of such expressions. In this work, we systematically evaluate four state-of-the-art large language models (LLMs) - Claude, GPT, Mistral, and Qwen - for dehumanization detection. Our results show that only one model-Claude-achieves strong performance (over 80% F1) under an optimized configuration, while others, despite their capabilities, perform only moderately. Performance drops further when distinguishing dehumanization from related hate types such as derogation. We also identify systematic disparities across target groups: models tend to over-predict dehumanization for some identities (e.g., Gay men), while under-identifying it for others (e.g., Refugees). These findings motivate the need for systematic, group-level evaluation when applying pretrained language models to dehumanization detection tasks.