Authors : Akshaya Acharya; Vibin Ravikumar; Bharani Kumar Depuru

Volume/Issue : Volume 10 - 2025, Issue 3 - March

Google Scholar : https://tinyurl.com/yc8ek495

Scribd : https://tinyurl.com/mszn2mp2

DOI : https://doi.org/10.38124/ijisrt/25mar1268

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The legal system in India is undergoing significant reforms with the introduction of the Bharatiya Nyaya Sanhita (BNS) [9], Bharatiya Nagarik Suraksha Sanhita (BNSS)[10], and Bharatiya Sakshya Adhiniyam (BSA)[11]. These new legal codes aim to modernize and simplify the legal framework, but they also pose challenges for legal professionals and litigants who must navigate these changes. This research proposes an AI-powered Legal Chatbot that leverages the BNS, BNSS, and BSA as its foundational knowledge base, while also integrating user-uploaded contextual documents, such as landmark judgments, to provide accurate and context-aware legal suggestions. The chatbot employs Google Generative AI Embeddings for text processing, FAISS (Facebook AI Similarity Search) for efficient similarity search, and Groq's LLaMA 3 (Large Language Model Meta AI) model for generating responses. By combining deep learning, natural language processing (NLP), this research establishes a scalable and reproducible framework for legal assistance, enabling users to receive precise legal advice and suggestions for litigative situations. The chatbot also provides real-time alerts and dynamically maps legal provisions, ensuring improved access to justice and streamlined legal research.

Keywords : Legal Chatbot, Bharatiya Nyaya Sanhita (BNS), Bharatiya Nagarik Suraksha Sanhita (BNSS), Bharatiya Sakshya Adhiniyam (BSA), AI in Legal Research, Contextual Document Integration, Landmark Judgments, Natural Language Processing (NLP), FAISS for Legal Search, CRISP-ML(Q) Methodology.

References :

[1]. Danilo S. Carvalho, Minh-Tien Nguyen, Tran Xuan Chien, Minh Le Nguyen. (2016). Lexical-Morphological Modeling for Legal Text Analysis https://doi.org/10.48550/arXiv.1609.00799

[2]. Koo-Rack Park (2021). Development of Artificial Intelligence-based Legal Counseling Chatbot System.  https://doi.org/10.9708/jksci.2021.26.03.029.

[3]. Ray Worthy Campbell, Artificial Intelligence in the Courtroom: The Delivery of Justice in the Age of Machine Learning, 18 COLO. TECH. L.J. 323 (2020). https://dx.doi.org/10.2139/ssrn.4425791

[4]. V A H Firdaus*, P Y Saputra, and D Suprianto (2019) Intelligence chatbot for Indonesian law on electronic information and transaction https://doi.org/10.1088/1757-899X/830/2/022089

[5]. Bunk, Tanja, Daksh Varshneya, Vladimir Vlasov, and Alan Nichol. 2020. DIET: Lightweight Language Understanding for Dialogue Systems. https://doi.org/10.48550/arXiv.2004.09936

[6]. Amato, F.; Fonisto, M.; Giacalone, M.; Sansone, C. An Intelligent Conversational Agent for the Legal Domain. Information 2023, 14, 307. https://doi.org/10.3390/info14060307

[7]. Omar, R., Mangukiya, O., Kalnis, P., and Mansour, E. (2023). Chatgpt versus traditional question answering for knowledge graphs: Current status and future directions towards knowledge graph chatbots. arXiv preprint arXiv:2302.06466.

[8]. Varada Socatiyanurak, Nittayapa Klangpornkun, Adirek Munthuli, Phongphan Phienphanich, Lalin Kovudhikulrungsri, Nantawat Saksakulkunakorn, Phonkanok Chairaungsri, Charturong Tantibundhit, "LAW-U: Legal Guidance Through Artificial Intelligence Chatbot for Sexual Violence Victims and Survivors" 2021, IEEE. https://doi.org/10.1109/ACCESS.2021.3113172.

[9]. Government of India, Bharatiya Nyaya Sanhita, BNS 2023. https://www.mha.gov.in/sites/default/files/250883_english_01042024.pdf.

[10]. Government of India, Bharatiya Nagarik Suraksha Sanhita 2023. https://www.mha.gov.in/sites/default/files/2024-04/250884_2_english_01042024.pdf

[11]. Government of India, Bharatiya SakshyaAdhiniyam, 2023. https://www.mha.gov.in/sites/default/files/2024-04/250882_english_01042024_0.pdf

[12]. Stefan Studer, Thanh Binh Bui, Christian Drescher, Alexander Hanuschkin, Ludwig Winkler, Steven Peters, Klaus-Robert Mueller (2021). Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology
https://doi.org/10.48550/arXiv.2003.05155.