A Multi-Stage Prompting and RAG Approach to Generating Legal Analysis in Common Law Systems

Titus T.H. Ng, Tien Hsuan Wu, Benjamin Minhao Chen, Yongxi Chen, Ben Kao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We explore the use of multi-stage prompting with retrieval-augmented generation (RAG) in generating legal analysis. We break the complex legal problems into small steps, including initial analysis, legal query formulation, legal sources retrieval, legal reasoning, result consolidation, and output generation. The design of this framework emulates the process a legal professional in a common law system approaches the problem.

Original languageEnglish
Title of host publicationLegal Knowledge and Information Systems - JURIX 2024
Subtitle of host publication37th Annual Conference
EditorsJaromir Savelka, Jakub Harasta, Tereza Novotna, Jakub Misek
PublisherIOS Press BV
Pages387-388
Number of pages2
ISBN (Electronic)9781643685625
DOIs
Publication statusPublished - 2024
Event37th Annual Conference on Legal Knowledge and Information Systems, JURIX 2024 - Brno, Czech Republic
Duration: 11 Dec 202413 Dec 2024

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume395
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference37th Annual Conference on Legal Knowledge and Information Systems, JURIX 2024
Country/TerritoryCzech Republic
CityBrno
Period11/12/2413/12/24

Fingerprint

Dive into the research topics of 'A Multi-Stage Prompting and RAG Approach to Generating Legal Analysis in Common Law Systems'. Together they form a unique fingerprint.

Cite this