PROSLEX: A Novel Dataset for Expert-Annotated Legal Statute Prediction for Indian Judiciary

2026-08-09

AI Summary

This study addresses the prevailing emphasis on prediction accuracy over interpretability and legal reasoning in existing statutory article prediction methods. To bridge this gap, the authors introduce PROSLEX, a novel dataset comprising 1,623 Indian legal documents and 7,450 expert-annotated legal rationales, enabling the first joint modeling of article prediction and legal reasoning explanation. The work proposes an evaluation framework tailored to judicial interpretability and leverages large language models with diverse prompting strategies—including zero-shot, few-shot, Chain-of-Thought (CoT), and Tree-of-Thought (ToT)—to perform multi-label classification and generate legally grounded explanations. Experimental results demonstrate that the proposed approach achieves a strong balance between predictive performance and the coherence and legal validity of generated explanations, establishing a new benchmark for interpretable legal AI systems.

Abstract

Legal Statute Prediction (LSP) involves automatically identifying relevant legal statutes given factual descriptions in legal documents, typically framed as a multi-label classification task within natural language processing and information retrieval research. While recent advances have begun incorporating Large Language Models (LLMs) for statute prediction, current approaches primarily focus on accuracy metrics without addressing the critical need for legal reasoning, a fundamental requirement in judicial contexts where decisions must be explainable and justifiable. To address this research gap, we present PROSLEX (PRediction Of Statutes and LEgal eXplanation), a comprehensive dataset comprising 1,623 expert-annotated legal documents from the Indian context. Each document is paired with statute predictions and detailed explanations, totaling 7,450 explanations, capturing the underlying legal reasoning. Using this dataset, we systematically evaluate various prompting strategies, including zero-shot, few-shot, chain-of-thought, and tree-of-thoughts approaches, to generate both statute predictions and their corresponding legal rationales. Our evaluation framework measures not only predictive performance but also the coherence and legal validity of generated explanations, positioning PROSLEX as a benchmark for developing explainable AI systems that can support legal practitioners while advancing research in interpretable legal NLP. To ensure reproducibility, we have made our PROSLEX dataset and model code available on GitHub: https://github.com/subinay494/Legal_Statute_Prediction_Explanation.

Problem

• Legal Statute Prediction
• Explainable AI
• Legal Reasoning
• Judicial Decision-Making
• Interpretable NLP

Innovation

• Legal Statute Prediction
• Explainable AI
• Expert-Annotated Dataset
• Legal Reasoning
• Chain-of-Thought Prompting