"

7 Generative AI and Legal Research

Theresa Buller

Note this page is based on information known to the authors at the time of writing (August 2025).

The application of artificial intelligence (AI) technologies in the legal sector is increasing and evolving rapidly as AI capabilities improve.

Generative AI such as ChatGPT, Perplexity AI and Copilot may help users to understand a legal topic and locate some legal sources. Generative AI tools are known to make things up or provide plausible but false ouputs, commonly known as hallucinations.

Guidance on the Use of AI in Aotearoa New Zealand

The rapid adoption of AI technologies has lead the Courts of New Zealand and the New Zealand Law Society to issue guidance on the use of generative AI:

Students should refer to the policies of their own institutions for guidance on the appropriate use and attribution of AI for study within their institution. Additionally, the diagram below describes seven factors to consider for the ethical use of generative AI, including the concepts of transparency, reliability, bias, equity, sustainability, data sovereignty and privacy.

A venn diagram made up of even ovals that meet in the middle. The middle central concept is Ethical AI. The concepts connected to it are: Transparency, reliability, bias, equity, sustainability, data sovereignty, and privacy
Know Your AI. By Kate Thompson. CC-BY-NC 4.0

Generative AI and Legal Research

Some ways in which generative AI can potentially be used in legal research include:

  • summarising complex texts, concepts and legal cases into plain language to aid understanding of topics and facilitate further research;
  • providing broad answers to common legal questions and general information relating to legal topics;
  • helping to identify key research concepts and create basic search strings;
  • conducting broad secondary legal research to guide primary research into case law and legislation;
  • brainstorming and generating ideas for further research.

It is important that legal researchers who use generative AI apply caution and critical evaluative judgement of outputs, fact-check for accuracy and verify all information sources, case law and legislation cited. They should be viewed as a tool to augment routine tasks but not as a replacement for legal interpretation and analysis. They can be used as a starting point for research but require careful verification for every output. Note: This is not an endorsement of the accuracy or efficacy of generative AI while undertaking legal research.

How to Use Generative AI Tools Effectively

A generative AI tool requires a prompt to produce content. When entering your prompt, provide thorough context, details and boundaries. A prompt can specify:

  • the points you want addressed;
  • the role or perspective from which the text should be written, for example, a legal practitioner;
  • the focus, format, style, intended audience and text length;
  • specific requirements, such as to be accurate and not creative in its response.

Prompting is an iterative process. Responses generally improve when additional questions are asked or rephrased.

Some basic prompt ideas:

For legal research and analysis:

Prompt: Act as a legal practitioner who is advising a client. Conduct legal research on [legal issue or topic]. Summarise the relevant case law and legislation in New Zealand. Provide analysis and conclusions based on your research. Be concise and accurate.

To uncover precedents:

Prompt: Act as a legal practitioner who is advising a client. Provide an overview of the legal precedents in [area of law]. List the leading cases that exist in this area of law and the key legal arguments for each case. Provide analysis and conclusions based on your research. Be concise and accurate.

Identify legislation and judgments for [legal issue]:

Prompt: Act as a legal practitioner who is preparing a case. What is the legislation relating to [legal issue] in New Zealand? List the leading cases that have cited this legislation and the key legal arguments for each case. Be concise and accurate.

The University of Arizona has a useful resource with ideas on writing prompts for legal research using generative AI. Their guide discusses the RICE (Role, Instructions, Context, Expectations) elements that can be incorporated into a prompt.

Risks and Benefits of Using Generative AI for Legal Research

Some of the key risks and benefits of using generative AI for legal research are:

Potential risks Potential benefits
  • Users need expertise to understand law and specific areas of the law in order to develop good prompts, ask effective questions and evaluate the genAI output for accuracy.
  • GenAI tools may suggest relevant case law that was missed during manual legal research.
  • Propensity of genAI tools to hallucinate and produce inaccurate, non-factual information.
  • GenAI tools may highlight discrepancies between jurisdictions that might initially be missed.
  • Hallucinations may include citing case law and legislation inaccurately.
  • Specific search skills, such as applying Boolean techniques, are not needed in genAI tools.
  • Output may be unrelated to the jurisdiction in question and not give enough depth or analysis for the specific legal topic.
  • Iterative prompting facilitates deeper diving into legal topic areas.
  • Bias, misinformation or disinformation may be present in genAI outputs owing to the generic, global nature of information it draws from and/or malicious actors.
  • GenAI tools can summarise large amounts of information to distil the critical matters faster.
  • Negligent use or the uploading of proprietary, confidential or copyrighted materials to genAI tools without applying professional judgement or the necessary genAI tool settings to meet professional and client obligations.
  • GenAI may weaken human capabilities to form ideas and to analyse, interpret and synthesise information.
  • Lack of user awareness of how AI and algorithms work may lead to over-reliance on genAI output.
  • Gen AI tools can use substantial amounts of energy and water to complete computations and raise serious issues around sustainability.

 

License

Icon for the Creative Commons Attribution-NonCommercial 4.0 International License

Generative AI and Legal Research Copyright © 2025 by Theresa Buller is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, except where otherwise noted.

Digital Object Identifier (DOI)

https://doi.org/10.18124/6f3q-bt16

Share This Book