Large language models as tax attorneys: a case study in legal capabilities emergence

Author:

Nay John J.1ORCID,Karamardian David2,Lawsky Sarah B.3,Tao Wenting2,Bhat Meghana4,Jain Raghav5,Lee Aaron Travis6,Choi Jonathan H.7,Kasai Jungo8

Affiliation:

1. CodeX, Center for Legal Informatics, Stanford University, Stanford, CA, USA

2. Stanford University, Stanford, CA, USA

3. Northwestern Pritzker School of Law, Chicago, IL, USA

4. Engineering, University of Michigan, Ann Arbor, MI, USA

5. SimPPL, India

6. Independent, Northern Ireland

7. School of Law, University of Southern California, Los Angeles, CA, USA

8. Department of Computer Science, University of Washington, Seattle, WA, USA

Abstract

Better understanding of Large Language Models' (LLMs) legal analysis abilities can contribute to improving the efficiency of legal services, governing artificial intelligence and leveraging LLMs to identify inconsistencies in law. This paper explores LLM capabilities in applying tax law. We choose this area of law because it has a structure that allows us to set up automated validation pipelines across thousands of examples, requires logical reasoning and maths skills, and enables us to test LLM capabilities in a manner relevant to real-world economic lives of citizens and companies. Our experiments demonstrate emerging legal understanding capabilities, with improved performance in each subsequent OpenAI model release. We experiment with retrieving and using the relevant legal authority to assess the impact of providing additional legal context to LLMs. Few-shot prompting, presenting examples of question–answer pairs, is also found to significantly enhance the performance of the most advanced model, GPT-4. The findings indicate that LLMs, particularly when combined with prompting enhancements and the correct legal texts, can perform at high levels of accuracy but not yet at expert tax lawyer levels. As LLMs continue to advance, their ability to reason about law autonomously could have significant implications for the legal profession and AI governance. This article is part of the theme issue ‘A complexity science approach to law and governance’.

Publisher

The Royal Society

Reference60 articles.

1. Benaich N Hogarth I. 2022 State of AI Report 2022. STATEOF.AI. 11 Oct 2022. See https://www.stateof.ai/2022-report-launch.html.

2. Wei J. 2022 137 Emergent Abilities of Large Language Models. JASONWEI.NET. 14 November 2022. See https://www.jasonwei.net/blog/emergence.

3. Webb T et al. 2022 Emergent Analogical Reasoning in Large Language Models. 19 December 2022. See https://arxiv.org/abs/2212.09196.

4. Hafner D et al. 2023 Mastering Diverse Domains through World Models. 10 January 2023. See https://arxiv.org/abs/2301.04104.

5. Institute for Human-Centered AI. 2023 STANFORD UNIV. [cited 20 March 2023]. See https://hai.stanford.edu.

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. AI generates covertly racist decisions about people based on their dialect;Nature;2024-08-28

2. Large language models and community legal centres: Could chatbots help reduce Australia’s justice gap?;Alternative Law Journal;2024-08-08

3. A complexity science approach to law and governance;Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences;2024-02-26

4. How to Use Large Language Models for Empirical Legal Research;Journal of Institutional and Theoretical Economics;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3