Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM48096
Volume:
9 |
5 |
May 2025
Pages:
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
This paper presents LegalRAG Assistant, an AI-powered legal chatbot platform that leverages Generative AI (GenAI), Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) to provide accurate, context-aware responses to legal queries. The system integrates Indian legal frameworks including the Bharatiya Nyaya Sanhita (BNS) and RERA guidelines to support real-time legal consultation and document analysis. A structured pipeline was developed using vector embeddings (via Sentence-BERT) and FAISS for efficient semantic retrieval of legal texts, which are then fed into a fine-tuned LLM (Mistral-7B-Instruct) for answer generation. The platform demonstrates over 90% retrieval precision on a curated legal dataset and supports multilingual, user-friendly interaction through a Gradio-based chatbot interface. Experimental outcomes emphasize LegalRAG Assistant’s readiness for deployment in legal advisory applications, especially in domains requiring rapid access to complex legal information with high accuracy and explainability.
KEYWORDS
Publication Date
5/17/2025
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...