IDEAS home Printed from https://ideas.repec.org/a/wly/empleg/v22y2025i2p216-242.html

Hallucination‐Free? Assessing the Reliability of Leading AI Legal Research Tools

Author

Listed:
  • Varun Magesh
  • Faiz Surani
  • Matthew Dahl
  • Mirac Suzgun
  • Christopher D. Manning
  • Daniel E. Ho

Abstract

Legal practice has witnessed a sharp rise in products incorporating artificial intelligence (AI). Such tools are designed to assist with a wide range of core legal tasks, from search and summarization of caselaw to document drafting. However, the large language models used in these tools are prone to “hallucinate,” or make up false information, making their use risky in high‐stakes domains. Recently, certain legal research providers have touted methods such as retrieval‐augmented generation (RAG) as “eliminating” or “avoid[ing]” hallucinations, or guaranteeing “hallucination‐free” legal citations. Because of the closed nature of these systems, systematically assessing these claims is challenging. In this article, we design and report on the first preregistered empirical evaluation of AI‐driven legal research tools. We demonstrate that the providers' claims are overstated. While hallucinations are reduced relative to general‐purpose chatbots (GPT‐4), we find that the AI research tools made by LexisNexis (Lexis+ AI) and Thomson Reuters (Westlaw AI‐Assisted Research and Ask Practical Law AI) each hallucinate between 17% and 33% of the time. We also document substantial differences between systems in responsiveness and accuracy. Our article makes four key contributions. It is the first to assess and report the performance of RAG‐based proprietary legal AI tools. Second, it introduces a comprehensive, preregistered dataset for identifying and understanding vulnerabilities in these systems. Third, it proposes a clear typology for differentiating between hallucinations and accurate legal responses. Last, it provides evidence to inform the responsibilities of legal professionals in supervising and verifying AI outputs, which remains a central open question for the responsible integration of AI into law.

Suggested Citation

  • Varun Magesh & Faiz Surani & Matthew Dahl & Mirac Suzgun & Christopher D. Manning & Daniel E. Ho, 2025. "Hallucination‐Free? Assessing the Reliability of Leading AI Legal Research Tools," Journal of Empirical Legal Studies, John Wiley & Sons, vol. 22(2), pages 216-242, June.
    • Handle: RePEc:wly:empleg:v:22:y:2025:i:2:p:216-242
    DOI: 10.1111/jels.12413
    as

    Download full text from publisher

    File URL: https://doi.org/10.1111/jels.12413
    Download Restriction: no
    File URL: https://libkey.io/10.1111/jels.12413?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Fowler, James H. & Johnson, Timothy R. & Spriggs, James F. & Jeon, Sangick & Wahlbeck, Paul J., 2007. "Network Analysis and the Law: Measuring the Legal Importance of Precedents at the U.S. Supreme Court," Political Analysis, Cambridge University Press, vol. 15(3), pages 324-346, July.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Monika Stachowiak-Kudła & Janusz Kudła, 2023. "Measuring the prestige of administrative courts," Quality & Quantity: International Journal of Methodology, Springer, vol. 57(4), pages 3637-3662, August.
    2. Grajzl, Peter & Murrell, Peter, 2024. "Caselaw and England's economic performance during the Industrial Revolution: Data and evidence," Journal of Comparative Economics, Elsevier, vol. 52(1), pages 145-165.
    3. Youjin Lee & Ashley L. Buchanan & Elizabeth L. Ogburn & Samuel R. Friedman & M. Elizabeth Halloran & Natallia V. Katenka & Jing Wu & Georgios K. Nikolopoulos, 2023. "Finding influential subjects in a network using a causal framework," Biometrics, The International Biometric Society, vol. 79(4), pages 3715-3727, December.
    4. Bommarito, Michael J. & Katz, Daniel Martin & Zelner, Jonathan L. & Fowler, James H., 2010. "Distance measures for dynamic citation networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 389(19), pages 4201-4208.
    5. Sandeep Soni & Kristina Lerman & Jacob Eisenstein, 2021. "Follow the leader: Documents on the leading edge of semantic change get more citations," Journal of the Association for Information Science & Technology, Association for Information Science & Technology, vol. 72(4), pages 478-492, April.
    6. Squintani, Francesco, 2024. "Strategic Disclosure in Networks," The Warwick Economics Research Paper Series (TWERPS) 1520, University of Warwick, Department of Economics.
    7. Squintani, Francesco, 2024. "Persuasion in Networks," CRETA Online Discussion Paper Series 88, Centre for Research in Economic Theory and its Applications CRETA.
    8. John Szmer & Robert K. Christensen & Samuel Grubbs, 2020. "What influences the influence of U.S. Courts of Appeals decisions?," European Journal of Law and Economics, Springer, vol. 49(1), pages 55-81, February.
    9. Ryan C. Black & James F. Spriggs, 2013. "The Citation and Depreciation of U.S. Supreme Court Precedent," Journal of Empirical Legal Studies, John Wiley & Sons, vol. 10(2), pages 325-358, June.
    10. Bokwon Lee & Kyu-Min Lee & Jae-Suk Yang, 2019. "Network structure reveals patterns of legal complexity in human society: The case of the Constitutional legal network," PLOS ONE, Public Library of Science, vol. 14(1), pages 1-15, January.
    11. Zahid Amadxarif & James Brookes & Nicola Garbarino & Rajan Patel & Eryk Walczak, 2019. "The language of rules: textual complexity in banking reforms," Bank of England working papers 834, Bank of England.
    12. Kazutaka Takechi, 2023. "How are the precedents of trade policy rules made under the World Trade Organization?," Economics and Politics, Wiley Blackwell, vol. 35(3), pages 806-821, November.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:wly:empleg:v:22:y:2025:i:2:p:216-242. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Wiley Content Delivery (email available below). General contact details of provider: https://doi.org/10.1111/(ISSN)1740-1461 .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.