Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?

Xiaoxi Kang, Lizhen Qu, Lay-Ki Soon, Adnan Trakic, Terry Yue Zhuo +2 more
10/23/2023
cs.CL

No official code found. Best implementation: christinakang/SIRAC (7 stars, last commit 2023-10-20).

Abstract

Large Language Models (LLMs), such as ChatGPT, have drawn a lot of attentions recently in the legal domain due to its emergent ability to tackle a variety of legal tasks. However, it is still unknown if LLMs are able to analyze a legal case and perform reasoning in the same manner as lawyers. Therefore, we constructed a novel corpus consisting of scenarios pertain to Contract Acts Malaysia and Australian Social Act for Dependent Child. ChatGPT is applied to perform analysis on the corpus using the IRAC method, which is a framework widely used by legal professionals for organizing legal analysis. Each scenario in the corpus is annotated with a complete IRAC analysis in a semi-structured format so that both machines and legal professionals are able to interpret and understand the annotations. In addition, we conducted the first empirical assessment of ChatGPT for IRAC analysis in order to understand how well it aligns with the analysis of legal professionals. Our experimental results shed lights on possible future research directions to improve alignments between LLMs and legal experts in terms of legal reasoning.

View on arXivView PDF

Code Implementations(1)

christinakang/SIRACCommunity100%

SIRAC : semi-structured IRAC(Issue, Rule, Analysis and Conclusion) corpus for legal scenarios

70PythonOct 12, 20233 years ago

Similar Papers

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

87% match1 repo5992023

Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need?

86% match2024

Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence

85% match2023

A Comprehensive Evaluation of Large Language Models on Legal Judgment Prediction

85% match1 repo132023

A Short Survey of Viewing Large Language Models in Legal Aspect

85% match1 repo3122023

Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models

85% match1 repo2023

Cite this paper

@article{kang2023chatgpt,
  title  = {Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?},
  author = {Xiaoxi Kang and Lizhen Qu and Lay-Ki Soon and Adnan Trakic and Terry Yue Zhuo and Patrick Charles Emerton and Genevieve Grant},
  year   = {2023},
  eprint = {2310.14880},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.14880v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.14880.svg)](https://codeofpaper.com/paper/2310.14880)

Discussion