Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918087945617408 |
|---|---|
| author | Saffari, Hamidreza Shafiei, Mohammadamin Zhang, Hezhao Harris, Lasana Moosavi, Nafise Sadat |
| author_facet | Saffari, Hamidreza Shafiei, Mohammadamin Zhang, Hezhao Harris, Lasana Moosavi, Nafise Sadat |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13818 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language Saffari, Hamidreza Shafiei, Mohammadamin Zhang, Hezhao Harris, Lasana Moosavi, Nafise Sadat Computation and Language 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. |
| title | Beyond Hate Speech: NLP's Challenges and Opportunities in Uncovering Dehumanizing Language |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.13818 |