Know Your Law: A Conventional AI Chatbot for Legal Awareness Using Retrieval Augmented Generation

Read full text Summarise with VIRAT
Authors: A Sri Pranav, R Diwakar, Balaji J, Dr. Paulraj D
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Access to legal information remains challenging for ordinary citizens due to the complexity and technical nature of statutory documents such as the Indian Penal Code (IPC). Traditional search systems often require precise legal terminology and return lengthy, difficult-to-understand texts. This paper presents Know Your Law, a Retrieval-Augmented Generation (RAG) based Conversational AI chatbot designed to simplify and improve access to legal knowledge. The system integrates hybrid retrieval using dense embeddings (Sentence Transformers) and sparse retrieval (BM25), supported by Pinecone vector storage, while a Large Language Model (LLaMA via Groq API) generates simplified, context-grounded responses. To ensure accuracy and ethical compliance, the system incorporates structured response validation, query filtering, and mandatory legal disclaimers. Experimental results demonstrate improved retrieval precision, reduced hallucination risk, and effective simplification of complex legal provisions, highlighting the potential of hybrid RAG systems in democratizing legal awareness.

Fields of Study & Subjects

Artificial Intelligence in Law Topic Modeling Information Retrieval and Search Behavior

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
22 March 2026
Language
EN