Fake news on social media platforms poses significant threats to public trust and information integrity. This research explores the application of quantum machine learning (QML) techniques for detecting fake news by leveraging quantum computing’s unique capabilities. Our work introduces a hybrid quantum-classical framework that utilizes quantum convolutional neural networks (QCNNs) with angle and amplitude encoding schemes for processing multimodal features from text and images. Experiments conducted on benchmark datasets - GossipCop and Politifact - demonstrate that our quantum-enhanced model achieves superior performance compared to classical approaches, with accuracy rates of 88.52% and 85.58%, and F1 scores of 93.19% and 90.20% respectively. Our findings establish QML as a viable approach for addressing the challenges of fake news detection in the digital era.

We address the challenge of retrieving previously fact-checked claims in mono-lingual and cross-lingual settings - a critical task given the global prevalence of disinformation. Our approach follows a two-stage strategy: a reliable baseline retrieval system using a fine-tuned embedding model and an LLM-based reranker. Our key contribution is demonstrating how LLM-based translation can overcome the hurdles of multilingual information retrieval. Additionally, we focus on ensuring that the bulk of the pipeline can be replicated on a consumer GPU. Our final integrated system achieved a success@10 score of 0.938 (~0.94) and 0.81025 on the monolingual and crosslingual test sets respectively.