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

Files

251009771v1.pdf (306.32 KB)

Links to Files

http://arxiv.org/abs/2510.09771

Permanent Link

https://doi.org/10.48550/arXiv.2510.09771
 http://hdl.handle.net/11603/40793

Collections

UMBC Student Collection
UMBC Computer Science and Electrical Engineering Department

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-9176-1782

Date

2025-10-10

Type of Work

journal articles
preprints
Text

Department

Program

Citation of Original Publication

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

UMBC Interactive Robotics and Language Lab
Computer Science - Computation and Language
Computer Science - Artificial Intelligence

Abstract

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.