# PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection

arXiv: https://arxiv.org/abs/2510.09771 · HTML: https://mlsanity.com/paper/2510.09771/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Low-resource Languages: A Review of Past Work and Future Challenges](https://mlsanity.com/paper/2006.07264/) (2020)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [Hate Speech detection in the Bengali language: A dataset and its baseline evaluation](https://mlsanity.com/paper/2012.09686/) (2020)
- [DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Language](https://mlsanity.com/paper/2012.14353/) (2020)
- [Multilingual Prompting for Improving LLM Generation Diversity](https://mlsanity.com/paper/2505.15229/) (2025)
- [Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis](https://mlsanity.com/paper/2308.10783/) (2023)
- [LLM-Based Multi-Task Bangla Hate Speech Detection: Type, Severity, and Target](https://mlsanity.com/paper/2510.01995/) (2025)
- [UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation](https://mlsanity.com/paper/2402.12730/) (2024)

## Abstract (arXiv)

The BLP-2025 Task 1A requires Bengali hate speech classification into six categories. Traditional supervised approaches need extensive labeled datasets that are expensive for low-resource languages. We developed PromptGuard, a few-shot framework combining chi-square statistical analysis for keyword extraction with adaptive majority voting for decision-making. We explore statistical keyword selection versus random approaches and adaptive voting mechanisms that extend classification based on consensus quality. Chi-square keywords provide consistent improvements across categories, while adaptive voting benefits ambiguous cases requiring extended classification rounds. PromptGuard achieves a micro-F1 of 67.61, outperforming n-gram baselines (60.75) and random approaches (14.65). Ablation studies confirm chi-square-based keywords show the most consistent impact across all categories.