Research Article
AttorneyGPT – Multilingual Generative Artificial Intelligence Law Chatbot using Retrieval Augmented Generation
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358089, author={A Adheshvar and P Jessiah Inbaraj and T Patturajan and K Rajesh}, title={AttorneyGPT -- Multilingual Generative Artificial Intelligence Law Chatbot using Retrieval Augmented Generation}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={attorneygpt multilingual ai legal chatbot retrieval-augmented generation (rag) natural language processing (nlp) large language models (llms) semantic search legal knowledge retrieval ai in law legal information systems}, doi={10.4108/eai.28-4-2025.2358089} }- A Adheshvar
P Jessiah Inbaraj
T Patturajan
K Rajesh
Year: 2025
AttorneyGPT – Multilingual Generative Artificial Intelligence Law Chatbot using Retrieval Augmented Generation
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358089
Abstract
The legal realm requires accurate context-embedded retrieval, which has to face with language boundaries as well as complex legal parlance. In this paper, we present AttorneyGPT, a multilingual generative AI law chatbot, and discuss the use of Retrieval-Augmented Generation (RAG) to improve the quality of legal guidance given. AttorneyGPT fuses NLP and LLM technology with domain-specific retrieval methods resulting in responses that are rooted in authoritative legal content. The system operates in different languages, to enable cross-jurisdictional legal support, while ensuring that facts are right and contextual fit is guaranteed. Our method improves semantic search, legal knowledge retrieval and response generation and thus mitigates hallucinations and enhances the legality of the chatbot.
