This research uses a Convolutional Neural Network (CNN) to predict bail judgements in India’s legal system, with a focus on Hindi legal documents. The study identifies a lack of machine learning implementation in India’s legal domain, especially in regional languages and lower courts. The CNN model used achieved an accuracy of 93% in bail prediction tasks, improving on the benchmark set by previous research. The authors highlight the potential of artificial intelligence in addressing the existing challenges in the legal system, such as the high number of pending cases and the language barrier in accessing legal resources.
Publication date: 26 Jan 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2401.14135
