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

• URL: http://arxiv.org/abs/2506.23930v1
• Date: Mon, 30 Jun 2025 14:59:25 GMT
• Title: Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages
• Authors: Ruhina Tabasshum Prome, Tarikul Islam Tamiti, Anomadarshi Barua,
• Abstract summary: This paper investigates how we can overcome the limitation via prompt engineering on large language models (LLMs) focusing on low-resource Bengali language.<n>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.<n>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.
• Score: 2.8811725782388686
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 CO$_2$ emissions, electricity usage, and computational time.

Related papers

• Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study [59.30098850050971]
  This work evaluates LLM prompting-based detection across eight non-English languages.<n>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.
  arXiv  Detail & Related papers  (2025-05-09T16:00:01Z)
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition [55.2480439325792]
  Speech Meta In-Context LEarning (SMILE) is an innovative framework that combines meta-learning with speech in-context learning (SICL)<n>We show that SMILE consistently outperforms baseline methods in training-free few-shot multilingual ASR tasks.
  arXiv  Detail & Related papers  (2024-09-16T16:04:16Z)
• Outcome-Constrained Large Language Models for Countering Hate Speech [10.434435022492723]
  This study aims to develop methods for generating counterspeech constrained by conversation outcomes. We experiment with large language models (LLMs) to incorporate into the text generation process two desired conversation outcomes. Evaluation results show that our methods effectively steer the generation of counterspeech toward the desired outcomes.
  arXiv  Detail & Related papers  (2024-03-25T19:44:06Z)
• Seamless: Multilingual Expressive and Streaming Speech Translation [71.12826355107889]
  We introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion. First, we contribute an improved version of the massively multilingual and multimodal SeamlessM4T model- SeamlessM4T v2. We bring major components from SeamlessExpressive and SeamlessStreaming together to form Seamless, the first publicly available system that unlocks expressive cross-lingual communication in real-time.
  arXiv  Detail & Related papers  (2023-12-08T17:18:42Z)
• Model-Agnostic Meta-Learning for Multilingual Hate Speech Detection [23.97444551607624]
  Hate speech in social media is a growing phenomenon, and detecting such toxic content has gained significant traction. HateMAML is a model-agnostic meta-learning-based framework that effectively performs hate speech detection in low-resource languages. Extensive experiments are conducted on five datasets across eight different low-resource languages.
  arXiv  Detail & Related papers  (2023-03-04T22:28:29Z)
• Zero-Shot Cross-lingual Aphasia Detection using Automatic Speech Recognition [3.2631198264090746]
  Aphasia is a common speech and language disorder, typically caused by a brain injury or a stroke, that affects millions of people worldwide. We propose an end-to-end pipeline using pre-trained Automatic Speech Recognition (ASR) models that share cross-lingual speech representations.
  arXiv  Detail & Related papers  (2022-04-01T14:05:02Z)
• Addressing the Challenges of Cross-Lingual Hate Speech Detection [115.1352779982269]
  In this paper we focus on cross-lingual transfer learning to support hate speech detection in low-resource languages. We leverage cross-lingual word embeddings to train our neural network systems on the source language and apply it to the target language. We investigate the issue of label imbalance of hate speech datasets, since the high ratio of non-hate examples compared to hate examples often leads to low model performance.
  arXiv  Detail & Related papers  (2022-01-15T20:48:14Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Cross-lingual hate speech detection based on multilingual domain-specific word embeddings [4.769747792846004]
  We propose to address the problem of multilingual hate speech detection from the perspective of transfer learning. Our goal is to determine if knowledge from one particular language can be used to classify other language. We show that the use of our simple yet specific multilingual hate representations improves classification results.
  arXiv  Detail & Related papers  (2021-04-30T02:24:50Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)
• Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network [3.0168410626760034]
  We build the largest Bengali word embedding models to date based on 250 million articles, which we call BengFastText. We incorporate word embeddings into a Multichannel Convolutional-LSTM network for predicting different types of hate speech, document classification, and sentiment analysis.
  arXiv  Detail & Related papers  (2020-04-11T22:17:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.