The rise in abusive language on social media is a significant threat to mental health and social cohesion. For Bengali speakers, the need for effective detection is critical. However, current methods fall short in addressing the massive volume of content. Improved techniques are urgently needed to combat online hate speech in Bengali. Traditional machine learning techniques, while useful, often require large, linguistically diverse datasets to train models effectively. This paper addresses the urgent need for improved hate speech detection methods in Bengali, aiming to fill the existing research gap. Contextual understanding is crucial in differentiating between harmful speech and benign expressions. Large language models (LLMs) have shown state-of-the-art performance in various natural language tasks due to their extensive training on vast amounts of data. We explore the application of LLMs, specifically GPT-3.5 Turbo and Gemini 1.5 Pro, for Bengali hate speech detection using Zero-Shot and Few-Shot Learning approaches. Unlike conventional methods, Zero-Shot Learning identifies hate speech without task-specific training data, making it highly adaptable to new datasets and languages. Few-Shot Learning, on the other hand, requires minimal labeled examples, allowing for efficient model training with limited resources. Our experimental results show that LLMs outperform traditional approaches. In this study, we evaluate GPT-3.5 Turbo and Gemini 1.5 Pro on multiple datasets. To further enhance our study, we consider the distribution of comments in different datasets and the challenge of class imbalance, which can affect model performance. The BD-SHS dataset consists of 35,197 comments in the training set, 7542 in the validation set, and 7542 in the test set. The Bengali Hate Speech Dataset v1.0 and v2.0 include comments distributed across various hate categories: personal hate (629), political hate (1771), religious hate (502), geopolitical hate (1179), and gender abusive hate (316). The Bengali Hate Dataset comprises 7500 non-hate and 7500 hate comments. GPT-3.5 Turbo achieved impressive results with 97.33%, 98.42%, and 98.53% accuracy. In contrast, Gemini 1.5 Pro showed lower performance across all datasets. Specifically, GPT-3.5 Turbo excelled with significantly higher accuracy compared to Gemini 1.5 Pro. These outcomes highlight a 6.28% increase in accuracy compared to traditional methods, which achieved 92.25%. Our research contributes to the growing body of literature on LLM applications in natural language processing, particularly in the context of low-resource languages.

Social media has increasingly relied on memes as a tool for expressing opinions, making meme sentiment analysis an emerging area of interest for researchers. While much of the research has focused on English-language memes, under-resourced languages, such as Bengali, have received limited attention. Given the surge in social media use, the need for sentiment analysis of memes in these languages has become critical. One of the primary challenges in this field is the lack of benchmark datasets, particularly in languages with fewer resources. To address this, we used the MemoSen dataset, designed for Bengali, which consists of 4368 memes annotated with three sentiment labels: positive, negative, and neutral. MemoSen is divided into training (70%), test (20%), and validation (10%) sets, with an imbalanced class distribution: 1349 memes in the positive class, 2728 in the negative class, and 291 in the neutral class. Our approach leverages advanced deep learning techniques for multimodal sentiment analysis in Bengali, introducing three hybrid approaches. SentimentTextFormer is a text-based, fine-tuned model that utilizes state-of-the-art transformer architectures to accurately extract sentiment-related insights from Bengali text, capturing nuanced linguistic features. SentimentImageFormer is an image-based model that employs cutting-edge transformer-based techniques for precise sentiment classification through visual data. Lastly, SentimentFormer is a hybrid model that seamlessly integrates both text and image modalities using fusion strategies. Early fusion combines textual and visual features at the input level, enabling the model to jointly learn from both modalities. Late fusion merges the outputs of separate text and image models, preserving their individual strengths for the final prediction. Intermediate fusion integrates textual and visual features at intermediate layers, refining their interactions during processing. These fusion strategies combine the strengths of both textual and visual data, enhancing sentiment analysis by exploiting complementary information from multiple sources. The performance of our models was evaluated using various accuracy metrics, with SentimentTextFormer achieving 73.31% accuracy and SentimentImageFormer attaining 64.72%. The hybrid model, SentimentFormer (SwiftFormer with mBERT), employing intermediate fusion, shows a notable improvement in accuracy, achieving 79.04%, outperforming SentimentTextFormer by 5.73% and SentimentImageFormer by 14.32%. Among the fusion strategies, SentimentFormer (SwiftFormer with mBERT) achieved the highest accuracy of 79.04%, highlighting the effectiveness of our fusion technique and the reliability of our multimodal framework in improving sentiment analysis accuracy across diverse modalities.

Medical Visual Question Answering (MedVQA) lies at the intersection of computer vision, natural language processing, and clinical decision-making, aiming to generate accurate responses from medical images paired with complex inquiries. Despite recent advances in vision–language models (VLMs), their use in healthcare remains limited by a lack of interpretability and a tendency to produce direct, unexplainable outputs. This opacity undermines their reliability in medical settings, where transparency and justification are critically important. To address this limitation, we propose a zero-shot chain-of-thought prompting framework that guides VLMs to perform multi-step reasoning before arriving at an answer. By encouraging the model to break down the problem, analyze both visual and contextual cues, and construct a stepwise explanation, the approach makes the reasoning process explicit and clinically meaningful. We evaluate the framework on the PMC-VQA benchmark, which includes authentic radiological images and expert-level prompts. In a comparative analysis of three leading VLMs, Gemini 2.5 Pro achieved the highest accuracy (72.48%), followed by Claude 3.5 Sonnet (69.00%) and GPT-4o Mini (67.33%). The results demonstrate that chain-of-thought prompting significantly improves both reasoning transparency and performance in MedVQA tasks.

The rise of abusive language on social media is a significant threat to mental health and 1 social cohesion. For Bengali speakers, the need for effective detection is critical. However, current 2 methods fall short in addressing the massive volume of content. Improved techniques are urgently 3 needed to combat online hate speech in Bengali. Traditional machine learning techniques, while 4 useful, often require large, linguistically diverse datasets to train models effectively. This paper 5 addresses the urgent need for improved hate speech detection methods in Bengali, aiming to fill the 6 existing research gap. Contextual understanding is crucial in differentiating between harmful speech 7 and benign expressions. Large language models (LLMs) have shown state-of-the-art performance in 8 various natural language tasks due to their extensive training on vast amounts of data. We explore the 9 application of LLMs, specifically GPT-3.5 Turbo and Gemini 1.5 Pro, for Bengali hate speech detection 10 using Zero-Shot and Few-Shot Learning approaches. Unlike conventional methods, Zero-Shot 11 Learning identifies hate speech without task-specific training data, making it highly adaptable to new 12 datasets and languages. Few-Shot Learning, on the other hand, requires minimal labeled examples, 13 allowing for efficient model training with limited resources. Our experimental results show that 14 LLMs outperform traditional approaches. In this study, we evaluated GPT-3.5 Turbo and Gemini 1.5 15 Pro on multiple datasets. To further enhance our study, we considered the distribution of comments 16 in different datasets and the challenge of class imbalance, which can affect model performance. The 17 BD-SHS dataset consists of 35,197 comments in the training set, 7,542 in the validation set, and 7,542 18 in the test set. The Bengali Hate Speech Dataset v1.0 & v2.0 includes comments distributed across 19 various hate categories: personal hate (629), political hate (1,771), religious hate (502), geopolitical hate 20 (1,179), and gender abusive hate (316). The Bengali Hate Dataset comprises 7,500 non-hate and 7,500 21 hate comments. GPT-3.5 Turbo achieved impressive results with 97.33%, 98.42%, and 98.53% accuracy. 22 In contrast, Gemini 1.5 Pro showed lower performance across all datasets. Specifically, GPT-3.5 Turbo 23 excelled with significantly higher accuracy compared to Gemini 1.5 Pro. These outcomes highlight a 24 6.28% increase in accuracy compared to traditional methods, which achieved 92.25%. Our research 25 contributes to the growing body of literature on LLM applications in natural language processing, 26 particularly in the context of low-resource languages.