International Journal on Science and Technology

E-ISSN: 2229-7677   •   Impact Factor: 9.88

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 17 Issue 2 April-June 2026 Submit your research before last 3 days of June to publish your research paper in the issue of April-June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 17 Issue 2
April-June 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Privacy-Preserving Legal Assistance: An Offline RAG-Based Large Language Model for the Indian Legal Context

Author(s) Mr. Abhishek Kumar Singh, Dr. Md Sajid Anwer
Country India
Abstract In this AI progressing World, there is a lot of legal work which can be done with the help of AI (LLM) with rapid rate and minimal human effort which makes it perfect for legal sector, but there is issue with how maximum LLM model works or integrated. Currently most of the LLMs are dependent on cloud-based system to operate which introduces data privacy risks for user also most of the LLMs are trained on the Western legal Dataset which introduces jurisdictional bias with respect to Indian laws. And third but very important issue with generalized models is “hallucination”. LLM models are trained in a way that they have to respond to the query confidently which makes it unreliable for domain specific work like Indian Constitution and Bharatiya Nyaya Sanhita (BNS). To handle these critical issues of LLMs in legal sector, this paper proposes a fully localized, offline architecture that work with the integration of RAFT (RAG + Fine Tuning) with 8-billion parameter Llama-3 model and Chroma DB pipeline. By implementing hallucination shield and Fine Tuning our model achieved a 95% retrieval accuracy on Indian penal statues and successfully blocked 75% of out of the bounds queries as compare to base model, which makes it perfect framework for privacy preserving offline legal AI.
Keywords Legal AI, LLM, RAG, RAFT, Llama3, Chroma DB, Indian Legal Context, GROQ, BNS, Indian Constitution
Field Engineering
Published In Volume 17, Issue 2, April-June 2026
Published On 2026-04-04
View / Download PDF File

Share this


CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 17 Isu 1Cover Page Vol 16 Isu 3Cover Page Vol 16 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJSAT
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us Message on WhatsApp +91-9687-182-185 editor@ijsat.org