Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research

The integration of generative artificial intelligence (GAI) in various domains has revolutionized traditional practices, and the legal sector is no exception. However, considering the hallucination of GAI, the correctness of generative outcome is not trustworthy. Hence, this paper presents a novel a...

Full description

Saved in:
Bibliographic Details
Main Author: Liu, Zihao
Other Authors: Jiang Xudong
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Law
Online Access:https://hdl.handle.net/10356/176464
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-176464
record_format dspace
spelling sg-ntu-dr.10356-1764642024-05-17T15:44:02Z Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research Liu, Zihao Jiang Xudong School of Electrical and Electronic Engineering EXDJiang@ntu.edu.sg Computer and Information Science Large language model (LLM) Law Retrieve-augmented generation (RAG) The integration of generative artificial intelligence (GAI) in various domains has revolutionized traditional practices, and the legal sector is no exception. However, considering the hallucination of GAI, the correctness of generative outcome is not trustworthy. Hence, this paper presents a novel and safe approach to legal consultation through AI chatting bots, aiming to enhance accessibility, efficiency, and accuracy in legal services. The chatting bot system discussed in this study utilizes natural language processing (NLP) and large language model (LLM) to understand and respond to legal queries from users. By analyzing vast legal databases and case precedents with a state-of-the-art technology: retrieve augmented generation (RAG), the AI chatting bot can provide insightful and contextually relevant information to users, offering guidance on legal matters ranging from contract interpretation to regulatory compliance. Key features of the AI chatting bot include personalized recommendations based on user input, real-time updates on legal developments, and interactive dialogue capabilities for clarifying complex legal concepts. Through a comparative analysis with traditional legal consultation methods, this paper analyzes characteristics of AI-powered chatting bots, such as cost-effectiveness, and scalability. Additionally, it explores the potential impact of AI chatting bots on improving access to justice, especially for underserved populations with limited resources for legal assistance. Overall, this research highlights the transformative potential of AI in the legal domain and underscores the importance of ethical considerations and continuous evaluation in deploying AI solutions for legal consultation. Bachelor's degree 2024-05-16T23:59:16Z 2024-05-16T23:59:16Z 2024 Final Year Project (FYP) Liu, Z. (2024). Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176464 https://hdl.handle.net/10356/176464 en A3070-231 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Large language model (LLM)
Law
Retrieve-augmented generation (RAG)
spellingShingle Computer and Information Science
Large language model (LLM)
Law
Retrieve-augmented generation (RAG)
Liu, Zihao
Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research
description The integration of generative artificial intelligence (GAI) in various domains has revolutionized traditional practices, and the legal sector is no exception. However, considering the hallucination of GAI, the correctness of generative outcome is not trustworthy. Hence, this paper presents a novel and safe approach to legal consultation through AI chatting bots, aiming to enhance accessibility, efficiency, and accuracy in legal services. The chatting bot system discussed in this study utilizes natural language processing (NLP) and large language model (LLM) to understand and respond to legal queries from users. By analyzing vast legal databases and case precedents with a state-of-the-art technology: retrieve augmented generation (RAG), the AI chatting bot can provide insightful and contextually relevant information to users, offering guidance on legal matters ranging from contract interpretation to regulatory compliance. Key features of the AI chatting bot include personalized recommendations based on user input, real-time updates on legal developments, and interactive dialogue capabilities for clarifying complex legal concepts. Through a comparative analysis with traditional legal consultation methods, this paper analyzes characteristics of AI-powered chatting bots, such as cost-effectiveness, and scalability. Additionally, it explores the potential impact of AI chatting bots on improving access to justice, especially for underserved populations with limited resources for legal assistance. Overall, this research highlights the transformative potential of AI in the legal domain and underscores the importance of ethical considerations and continuous evaluation in deploying AI solutions for legal consultation.
author2 Jiang Xudong
author_facet Jiang Xudong
Liu, Zihao
format Final Year Project
author Liu, Zihao
author_sort Liu, Zihao
title Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research
title_short Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research
title_full Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research
title_fullStr Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research
title_full_unstemmed Large language model (LLM) with retrieve-augmented generation (RAG) for legal case research
title_sort large language model (llm) with retrieve-augmented generation (rag) for legal case research
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/176464
_version_ 1806059862840311808