# Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study

arXiv: https://arxiv.org/abs/2505.06149 · HTML: https://mlsanity.com/paper/2505.06149/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 20 of 20)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond](https://mlsanity.com/paper/2104.12250/) (2021)
- [Multilingual Instruction Tuning With Just a Pinch of Multilinguality](https://mlsanity.com/paper/2401.01854/) (2024)
- [Probing LLMs for hate speech detection: strengths and vulnerabilities](https://mlsanity.com/paper/2310.12860/) (2023)
- [Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models](https://mlsanity.com/paper/2206.09917/) (2022)
- ["HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media](https://mlsanity.com/paper/2304.10619/) (2023)
- [Large-Scale Hate Speech Detection with Cross-Domain Transfer](https://mlsanity.com/paper/2203.01111/) (2022)
- [When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks](https://mlsanity.com/paper/2311.08993/) (2023)
- [Hate Personified: Investigating the role of LLMs in content moderation](https://mlsanity.com/paper/2410.02657/) (2024)
- [Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs](https://mlsanity.com/paper/2410.03730/) (2024)
- [Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settings](https://mlsanity.com/paper/2410.13153/) (2024)
- [Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset](https://mlsanity.com/paper/2403.19559/) (2024)
- [Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection](https://mlsanity.com/paper/2410.15623/) (2024)
- [Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization](https://mlsanity.com/paper/2502.19612/) (2025)

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

- [MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations](https://mlsanity.com/paper/2508.00760/) (2025)
- [On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs](https://mlsanity.com/paper/2510.05864/) (2025)
- [HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations](https://mlsanity.com/paper/2601.13547/) (2026)
- [You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism](https://mlsanity.com/paper/2607.04945/) (2026)
- [Introducing the Privacy-HSD Trade-off: Hate Speech Detection, but not at the Cost of Privacy](https://mlsanity.com/paper/2608.19006/) (2026)
- ['Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection](https://mlsanity.com/paper/2608.24191/) (2026)
- [From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation](https://mlsanity.com/paper/2608.25605/) (2026)

## Abstract (arXiv)

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.