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

• URL: http://arxiv.org/abs/2605.01292v1
• Date: Sat, 02 May 2026 07:02:29 GMT
• Title: Addressing Data Scarcity in Bangla Fake News Detection: An LLM-Based Dataset Augmentation Approach
• Abstract summary: This study investigates whether Large Language Model (LLM) based augmentation can effectively address the limitation and improve Bangla fake news classification.<n>Existing datasets remain valuable but highly imbalanced, limiting model performance.<n>We propose a systematic augmentation framework that generates synthetic Bangla news articles using the instruction tuned Gemma 3 27B IT model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Bangla BERT for Hyperpartisan News Detection: A Semi-Supervised and Explainable AI Approach [0.0]
  State-of-the-art transformer-based model designed to enhance classification accuracy for hyperpartisan news.<n>With a remarkable accuracy score of 95.65%, Bangla BERT outperforms conventional approaches.
  arXiv  Detail & Related papers  (2025-07-28T18:02:01Z)
• Breaking the Fake News Barrier: Deep Learning Approaches in Bangla Language [0.0]
  This ponder presents a strategy that utilizes a profound learning innovation, particularly the Gated Repetitive Unit (GRU) to recognize fake news within the Bangla dialect.<n>The strategy of our proposed work incorporates intensive information preprocessing, which includes tlemmaization, tokenization, and tending to course awkward nature by oversampling.<n>The performance of the model is investigated by reliable metrics like precision, recall, F1 score, and accuracy.
  arXiv  Detail & Related papers  (2025-01-30T21:41:26Z)
• From Scarcity to Capability: Empowering Fake News Detection in Low-Resource Languages with LLMs [0.6086698578975425]
  BanFakeNews-2.0 is a robust dataset to enhance Bangla fake news detection.<n>This version includes 11,700 additional, meticulously curated fake news articles validated from credible sources.<n>In addition, we created a manually curated independent test set of 460 fake and 540 authentic news items.
  arXiv  Detail & Related papers  (2025-01-16T15:24:41Z)
• Detect, Investigate, Judge and Determine: A Knowledge-guided Framework for Few-shot Fake News Detection [53.41813030290324]
  Few-Shot Fake News Detection (FS-FND) aims to distinguish inaccurate news from real ones in extremely low-resource scenarios.<n>This task has garnered increased attention due to the widespread dissemination and harmful impact of fake news on social media.<n>We propose a Dual-perspective Knowledge-guided Fake News Detection (DKFND) model, designed to enhance LLMs from both inside and outside perspectives.
  arXiv  Detail & Related papers  (2024-07-12T03:15:01Z)
• ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs [60.81649785463651]
  We introduce ExaRanker-Open, where we adapt and explore the use of open-source language models to generate explanations. Our findings reveal that incorporating explanations consistently enhances neural rankers, with benefits escalating as the LLM size increases.
  arXiv  Detail & Related papers  (2024-02-09T11:23:14Z)
• Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models [0.07696728525672149]
  We propose a methodology consisting of four distinct approaches to classify fake news articles in Bengali.<n>Our approach includes translating English news articles and using augmentation techniques to curb the deficit of fake news articles.<n>We show the effectiveness of summarization and augmentation in the case of Bengali fake news detection.
  arXiv  Detail & Related papers  (2023-07-13T14:50:55Z)
• Multiverse: Multilingual Evidence for Fake News Detection [71.51905606492376]
  Multiverse is a new feature based on multilingual evidence that can be used for fake news detection. The hypothesis of the usage of cross-lingual evidence as a feature for fake news detection is confirmed.
  arXiv  Detail & Related papers  (2022-11-25T18:24:17Z)
• Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation [105.20743048379387]
  We propose a novel framework for generating training examples informed by the known styles and strategies of human-authored propaganda. Specifically, we perform self-critical sequence training guided by natural language inference to ensure the validity of the generated articles. Our experimental results show that fake news detectors trained on PropaNews are better at detecting human-written disinformation by 3.62 - 7.69% F1 score on two public datasets.
  arXiv  Detail & Related papers  (2022-03-10T14:24:19Z)
• Revisiting Self-Training for Few-Shot Learning of Language Model [61.173976954360334]
  Unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
  arXiv  Detail & Related papers  (2021-10-04T08:51:36Z)
• Ranking Creative Language Characteristics in Small Data Scenarios [52.00161818003478]
  We adapt the DirectRanker to provide a new deep model for ranking creative language with small data. Our experiments with sparse training data show that while the performance of standard neural ranking approaches collapses with small datasets, DirectRanker remains effective.
  arXiv  Detail & Related papers  (2020-10-23T18:57:47Z)
• BanFakeNews: A Dataset for Detecting Fake News in Bangla [1.4170999534105675]
  We propose an annotated dataset of 50K news that can be used for building automated fake news detection systems. We develop a benchmark system with state of the art NLP techniques to identify Bangla fake news.
  arXiv  Detail & Related papers  (2020-04-19T07:42:22Z)

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.