Addressing Data Scarcity in Bangla Fake News Detection: An LLM-Based Dataset Augmentation Approach

TL;DR

This paper explores using LLM-based data augmentation to improve Bangla fake news detection, demonstrating significant performance gains and releasing a synthetic dataset for low-resource language research.

Contribution

It introduces a systematic LLM augmentation framework for Bangla fake news datasets, enhancing classification performance and supporting reproducibility with publicly released data and code.

Findings

Augmenting only the minority class with high augmentation rate improves F1 score from 0.85 to 0.88.

Random subsampling combined with augmentation yields the strongest gains.

Generated 4,545 synthetic Bangla fake news samples for research use.

Abstract

The growing spread of misinformation in digital media highlights the need for reliable fake news detection systems, yet progress in under-resourced languages such as Bangla is limited by small and imbalanced datasets. This study investigates whether Large Language Model (LLM) based augmentation can effectively address this limitation and improve Bangla fake news classification. Existing datasets remain valuable but highly imbalanced, limiting model performance, and LLM based augmentation for Bangla has been scarcely explored. To fill this gap, we propose a systematic augmentation framework that generates synthetic Bangla news articles using the instruction tuned Gemma 3 27B IT model, supported by semantic filtering and controlled subsampling to preserve label consistency and diversity. We compare zero shot and few shot prompting, evaluate multiple augmentation rates, and examine random versus similarity-based selection strategies. Our experiments show that augmenting only the minority class with a high augmentation rate and random subsampling yields the strongest gains, raising the Fake News F1 score from 0.85 to 0.88. To support reproducibility and further research in this low-resource domain, we publicly release 4,545 synthetically generated Bangla fake news samples along with our full implementation. These findings demonstrate that well-designed LLM-driven augmentation can significantly improve fake news detection in low resource settings and provide a practical foundation for advancing multilingual misinformation research.