# Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages

arXiv: https://arxiv.org/abs/2506.23930 · HTML: https://mlsanity.com/paper/2506.23930/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 66 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models](https://mlsanity.com/paper/2403.17336/) (2024)
- [Learning from others' mistakes: Avoiding dataset biases without modeling them](https://mlsanity.com/paper/2012.01300/) (2020)
- [Don't Say No: Jailbreaking LLM by Suppressing Refusal](https://mlsanity.com/paper/2404.16369/) (2024)
- [A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1610.08815/) (2016)
- [Don't Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection](https://mlsanity.com/paper/2402.11406/) (2024)
- [Towards Climate Awareness in NLP Research](https://mlsanity.com/paper/2205.05071/) (2022)
- [Hate Speech and Offensive Language Detection in Bengali](https://mlsanity.com/paper/2210.03479/) (2022)
- [Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2312.15099/) (2023)
- [BNLP: Natural language processing toolkit for Bengali language](https://mlsanity.com/paper/2102.00405/) (2021)
- [A Dictionary-based Approach to Racism Detection in Dutch Social Media](https://mlsanity.com/paper/1608.08738/) (2016)
- [A Web of Hate: Tackling Hateful Speech in Online Social Spaces](https://mlsanity.com/paper/1709.10159/) (2017)
- [HateCheckHIn: Evaluating Hindi Hate Speech Detection Models](https://mlsanity.com/paper/2205.00328/) (2022)
- [Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model](https://mlsanity.com/paper/2412.02802/) (2024)
- [BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts](https://mlsanity.com/paper/2206.00372/) (2022)
- [Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset](https://mlsanity.com/paper/2403.19559/) (2024)
- [QutNocturnal@HASOC'19: CNN for Hate Speech and Offensive Content Identification in Hindi Language](https://mlsanity.com/paper/2008.12448/) (2020)
- [Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages](https://mlsanity.com/paper/2409.04512/) (2024)
- [An energy-based comparative analysis of common approaches to text classification in the Legal domain](https://mlsanity.com/paper/2311.01256/) (2023)
- [Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions](https://mlsanity.com/paper/2401.07847/) (2024)

## Abstract (arXiv)

The rapid expansion of social media leads to a marked increase in hate speech, which threatens personal lives and results in numerous hate crimes. Detecting hate speech presents several challenges: diverse dialects, frequent code-mixing, and the prevalence of misspelled words in user-generated content on social media platforms. Recent progress in hate speech detection is typically concentrated on high-resource languages. However, low-resource languages still face significant challenges due to the lack of large-scale, high-quality datasets. This paper investigates how we can overcome this limitation via prompt engineering on large language models (LLMs) focusing on low-resource Bengali language. We investigate six prompting strategies - zero-shot prompting, refusal suppression, flattering the classifier, multi-shot prompting, role prompting, and finally our innovative metaphor prompting to detect hate speech effectively in low-resource languages. We pioneer the metaphor prompting to circumvent the built-in safety mechanisms of LLMs that marks a significant departure from existing jailbreaking methods. We investigate all six different prompting strategies on the Llama2-7B model and compare the results extensively with three pre-trained word embeddings - GloVe, Word2Vec, and FastText for three different deep learning models - multilayer perceptron (MLP), convolutional neural network (CNN), and bidirectional gated recurrent unit (BiGRU). To prove the effectiveness of our metaphor prompting in the low-resource Bengali language, we also evaluate it in another low-resource language - Hindi, and two high-resource languages - English and German. The performance of all prompting techniques is evaluated using the F1 score, and environmental impact factor (IF), which measures CO2 emissions, electricity usage, and computational time.