Article Info

Published 23 Apr 2026

Volume / Issue 2 / Issue 4

Pages 125–134

DOI

10.64823/ijter.2604015

399 views

190 downloads

In This Issue

From Refinery to Road: Execution of Fuel Logistics & Market Adaptation

Anuj Santosh Jagadale

ANN-Enhanced Adaptive Sliding-Mode Control for STATCOM- Assisted Self-Excited Induction Generator in Wind Energy Conversion Systems

S. Radha Krishna Reddy

Empowering Researchers in the AI Era: A Study of Emerging Tools, Applications, and Impact

Vivek Kumar Saxena

Comparative Study of Mono and Hybrid Nanofluids in MQL Turning of AISI 1040 Steel Using Box–Behnken RSM Approach

Mr. Altaf Nalbandh

Design of Intelligent Energy Meter with IoT-Based Power Theft Detection

Mayuresh Desai

A Drift-Aware One-Class SVM Framework for Real-Time Adaptive DDoS Detection in SDN Environments

Priti Tukaram Chorade

Open Access Research Article

10 pages PDF

RAG-Based Legal Research Assistant for Finding Similar Past Cases

Shivanand R Koppalkar

Research

0009-0009-7843-2595 Website ResearchGate LinkedIn

About

28+ years experience architecting innovative product and technology software development in the Financials Services, Utilities, Insurance, Product Development, Human Resources Management (HRMS), Supply Chain & Logistics, Self service, Procure to Pay, Order Fulfillment, Oracle Data Integration, Oracle Enterprise Data Quality, Oracle Business Intelligence, Project Management, SOX Compliance and Information Systems Risk & Compliance, Chartered Wealth Management, Chartered Asset Management, Financial Derivative Products & Instruments and International Transfer Pricing, Mortgages - Individual & Businesses, Data Warehousing and Oracle Analytics Cloud (Fusion Analytics Warehouse). Specialties: Expertise in the Product and Custom Application Development experience in the domain areas of Financial Services, Utilities, Insurance, Human Resources Management (HRMS), Supply Chain and Logistics, and Customer Relationship Management (CRM) and Product Development. Financial Derivative Products & Instruments and International Transfer Pricing, Agile Methodologies - Certified Scrum Master & Certified Scrum Product Owner Accreditations, Certificate in Options, Predictive Analytics, Futures and Derivatives from London School of Business & Finance (LSBF), Big Data, HADOOP, MapReduce, HDFS, Hive, HBase, PIG and Flume, Oracle Fusion Financials, P2P, PPM and PBCS, Inventory and Supply Chain Management Cloud, No Code AI & Machine Learning: Building Data Science Solutions, Cornell AI Strategy Program

Research Interests

Artificial Intelligence Machine Learning Deep Learning Neural Networks Generative AI Agentic AI AI Agents

International Journal of Technology and Emerging Research 2026 , 2 (4) , 125–134

10.64823/ijter.2604015

Published: 23 Apr 2026

View PDF Download

Cite this article

APA

Shivanand R Koppalkar (2026). RAG-Based Legal Research Assistant for Finding Similar Past Cases. International Journal of Technology and Emerging Research, 2(4): 125–134. https://doi.org/10.64823/ijter.2604015

MLA

Shivanand R Koppalkar "RAG-Based Legal Research Assistant for Finding Similar Past Cases." International Journal of Technology and Emerging Research, vol. 2, no. 4, 2026, pp. 125–134. https://doi.org/10.64823/ijter.2604015

Chicago

Shivanand R Koppalkar. "RAG-Based Legal Research Assistant for Finding Similar Past Cases." International Journal of Technology and Emerging Research 2, no. 4 (2026): 125–134. https://doi.org/10.64823/ijter.2604015

BibTeX

@article{Shivanand R Koppalkar2026rag-based, author = {Shivanand R Koppalkar}, title = {RAG-Based Legal Research Assistant for Finding Similar Past Cases}, journal = {International Journal of Technology and Emerging Research}, year = {2026}, volume = {2}, number = {4}, pages = {125–134}, doi = {10.64823/ijter.2604015}, }

Abstract

This paper presents the design, architecture, and evaluation of a Retrieval-Augmented Generation system that assists new legal assistants in locating connected and similar past cases for new filings. The solution addresses Job 1, Legal Assistant, and leverages a curated Knowledge Base of 10 structured research session logs spanning five practice areas at a fictional law firm. Generative AI is assessed as capable of handling approximately 80 percent of the task, with the remaining 20 percent requiring human legal judgment, case validity verification, and jurisdiction-specific reasoning. The RAG architecture pairs a HuggingFace sentence transformer embedding model with FAISS vector search and GPT-4o-mini for grounded generation. Three query enhancement techniques improve retrieval precision beyond the baseline. Evaluation across eight metrics covering retrieval quality, generation quality through the RAG Triad, and operational performance demonstrates that the solution meets or exceeds the 0.80 target threshold on seven of eight dimensions. The paper documents limitations in cost, latency, case law currency, and the irreplaceable need for attorney oversight.

Keywords: Retrieval-Augmented Generation, RAG, legal research, pre-trained models, FAISS, groundedness, faithfulness, knowledge base, GenAI evaluation, legal assistant

© 2026 The Author(s). Published by IORO Publications. This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, distribution, and reproduction in any medium, provided the original author and source are credited, a link to the license is provided, and any changes are indicated.