NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law System

2025-08-01

AI Summary

Existing judgment prediction models for India’s common law system overlook the dual reliance on statutory provisions and binding precedents. Method: This paper proposes a retrieval-augmented generation (RAG) framework integrating case facts, statutory texts, and judicial precedents. It introduces, for the first time in the Indian legal context, joint semantic retrieval of statutes and precedents, enhanced by domain-adapted legal text matching and LLM-based evaluation (e.g., G-Eval). Contribution/Results: The framework delivers an interpretable prediction system aligned with real-world judicial reasoning. By injecting structured legal knowledge—explicitly modeling statutory authority and precedent hierarchy—it significantly improves both prediction accuracy and the quality of legal justification. Experiments demonstrate superior performance over conventional methods relying solely on intra-case textual features.

Technology Category

• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Machine Learning: Learning Preferences or Rankings
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Legal Judgment Prediction (LJP) has emerged as a key area in AI for law, aiming to automate judicial outcome forecasting and enhance interpretability in legal reasoning. While previous approaches in the Indian context have relied on internal case content such as facts, issues, and reasoning, they often overlook a core element of common law systems, which is reliance on statutory provisions and judicial precedents. In this work, we propose NyayaRAG, a Retrieval-Augmented Generation (RAG) framework that simulates realistic courtroom scenarios by providing models with factual case descriptions, relevant legal statutes, and semantically retrieved prior cases. NyayaRAG evaluates the effectiveness of these combined inputs in predicting court decisions and generating legal explanations using a domain-specific pipeline tailored to the Indian legal system. We assess performance across various input configurations using both standard lexical and semantic metrics as well as LLM-based evaluators such as G-Eval. Our results show that augmenting factual inputs with structured legal knowledge significantly improves both predictive accuracy and explanation quality.

Problem

• Predicting court decisions in Indian common law system
• Enhancing legal reasoning with statutes and precedents
• Improving judgment accuracy and explanation quality

Innovation

• RAG framework for legal judgment prediction
• Combines case facts with legal statutes
• Semantic retrieval of prior cases