Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909621828976640 |
|---|---|
| author | Ghorbanpour, Faeze Dementieva, Daryna Fraser, Alexander |
| author_facet | Ghorbanpour, Faeze Dementieva, Daryna Fraser, Alexander |
| contents | Despite growing interest in automated hate speech detection, most existing approaches overlook the linguistic diversity of online content. Multilingual instruction-tuned large language models such as LLaMA, Aya, Qwen, and BloomZ offer promising capabilities across languages, but their effectiveness in identifying hate speech through zero-shot and few-shot prompting remains underexplored. This work evaluates LLM prompting-based detection across eight non-English languages, utilizing several prompting techniques and comparing them to fine-tuned encoder models. We show that while zero-shot and few-shot prompting lag behind fine-tuned encoder models on most of the real-world evaluation sets, they achieve better generalization on functional tests for hate speech detection. Our study also reveals that prompt design plays a critical role, with each language often requiring customized prompting techniques to maximize performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06149 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study Ghorbanpour, Faeze Dementieva, Daryna Fraser, Alexander Computation and Language Computers and Society Multimedia Despite growing interest in automated hate speech detection, most existing approaches overlook the linguistic diversity of online content. Multilingual instruction-tuned large language models such as LLaMA, Aya, Qwen, and BloomZ offer promising capabilities across languages, but their effectiveness in identifying hate speech through zero-shot and few-shot prompting remains underexplored. This work evaluates LLM prompting-based detection across eight non-English languages, utilizing several prompting techniques and comparing them to fine-tuned encoder models. We show that while zero-shot and few-shot prompting lag behind fine-tuned encoder models on most of the real-world evaluation sets, they achieve better generalization on functional tests for hate speech detection. Our study also reveals that prompt design plays a critical role, with each language often requiring customized prompting techniques to maximize performance. |
| title | Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study |
| topic | Computation and Language Computers and Society Multimedia |
| url | https://arxiv.org/abs/2505.06149 |