A Data Science Approach to Calcutta High Court Judgments: An Efficient LLM and RAG-powered Framework for Summarization and Similar Cases Retrieval

2025-06-28

AI Summary

To address the challenges of lengthy judgment texts and inefficient case retrieval in the Calcutta High Court, this study proposes an end-to-end legal intelligence analysis framework integrating fine-tuned PEGASUS with Retrieval-Augmented Generation (RAG). Methodologically, we introduce a novel two-stage summarization pipeline: first, extracting salient legal elements to generate semantically coherent, concise summaries; second, constructing a high-quality vector database for semantic retrieval. RAG is then employed to enable precise, semantics-driven case matching. The framework significantly enhances legal text comprehension and information access efficiency, outperforming baseline models in both summary quality (ROUGE-L +12.3%) and retrieval accuracy (Top-5 Recall +18.7%). This work establishes a scalable, interpretable AI-assisted decision-making paradigm tailored for resource-constrained judicial systems.

Technology Category

• Natural Language Processing: Summarization
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

The judiciary, as one of democracy's three pillars, is dealing with a rising amount of legal issues, needing careful use of judicial resources. This research presents a complex framework that leverages Data Science methodologies, notably Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) techniques, to improve the efficiency of analyzing Calcutta High Court verdicts. Our framework focuses on two key aspects: first, the creation of a robust summarization mechanism that distills complex legal texts into concise and coherent summaries; and second, the development of an intelligent system for retrieving similar cases, which will assist legal professionals in research and decision making. By fine-tuning the Pegasus model using case head note summaries, we achieve significant improvements in the summarization of legal cases. Our two-step summarizing technique preserves crucial legal contexts, allowing for the production of a comprehensive vector database for RAG. The RAG-powered framework efficiently retrieves similar cases in response to user queries, offering thorough overviews and summaries. This technique not only improves legal research efficiency, but it also helps legal professionals and students easily acquire and grasp key legal information, benefiting the overall legal scenario.

Problem

• Summarizing complex legal texts efficiently
• Retrieving similar legal cases intelligently
• Enhancing legal research and decision-making

Innovation

• Uses LLM for legal text summarization
• Implements RAG for similar case retrieval
• Fine-tunes Pegasus model for improved accuracy