We propose a novel dataset for detecting religious hate speech in the context of elections in Karnataka, with a particular focus on Kannada and Kannada-English code-mixed text. The data was collected during the Karnataka state elections and includes 3,000 labeled samples that reflect various forms of online discourse related to religion. This dataset aims to address the growing concern of religious intolerance and hate speech during election periods, it’s a dataset of multilingual, code-mixed language. To evaluate the effectiveness of this dataset, we benchmarked it using the latest state-of-the-art algorithms. We achieved accuracy of 78.61%.

Advanced AI models that generate realistic images from text prompts offer new creative possibilities but also risk producing culturally insensitive or offensive content. To address this issue, we introduce a novel dataset designed to classify text prompts that could lead to the generation of harmful images misrepresenting different cultures and communities. By training machine learning models on this dataset, we aim to automatically identify and filter out harmful prompts before image generation, balancing cultural sensitivity with creative freedom. Benchmarking with state-ofthe-art language models, our baseline models achieved an accuracy of 73.34%.