Law.com | The Premier Source for Global Legal News & Analysis

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

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. But 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" (Casetext, 2023) or "avoid[ing]" hallucinations (Thomson Reuters, 2023), or guaranteeing "hallucination-free" legal citations (LexisNexis, 2023). 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.

Governing Digital Legal Systems: Insights on Artificial Intelligence and Rules as Code · MIT Computational Law Report

This article explores how AI and 'rules as code' are turning law into automated systems. It highlights the need for governance focused on transparency, explainability, and risk management to ensure these digital legal frameworks stay reliable and fair.

Steal the Internet - Archiving Everything and Sharing It With Others

2014: 70% of the links within legal journals and 50% of the URLs from Supreme Court decisions did not contain the originally cited material.

Robert Diab

A blog about law and technology with a focus on privacy, online harms, and expression

AI Hallucination Cases Database – Damien Charlotin

The most comprehensive database of AI hallucination cases in law: legal decisions from courts worldwide, searchable by country, party, AI tool, and outcome. Updated daily.

Litigation Tracker: Legal Challenges to Trump Administration Actions

A public resource tracking the legal challenges to the Trump administration's executive orders and actions.

“The Template for Law Schools Around the World”: UChicago Law School Announces New AI Strategy

The Law School will prohibit electronic devices in most 1L courses next academic year, according to a broad strategy statement outlining its new approach to legal education amid increasing use of AI at universities and in the field.

Wex

Wex is a free legal dictionary and encyclopedia sponsored and hosted by the Legal Information Institute at Cornell Law School. The goal of the Wex project is to use law students to demystify legal language to the best of our collective ability. Nothing in Wex should be construed as legal advice, nor should it be considered to be the position or opinion of Cornell University, Cornell Law School, or the faculty of either. More information about Wex can be found in our Wex Definitions page. Here's a list of all pages.

Editor's Notes: Can We Defy Courts While Believing In Rule of Law?

Do our tactics throw out democracy and rule of law while purportedly aiming at saving them?

Judge Learns Lawyers on Both Sides of Case Used AI, Cancels Trial, Kicks Everyone Off the Case

When two AIs argue against each other, the legal system loses.

Supreme Court - Recently Posted Judgments

This webpage lists judgments recently released by the Supreme Court and provides links to copies of those judgments.

Meet the Author: Alicia Solow-Niederman

Alicia Solow-NiedermanAssociate Professor of LawGeorge Washington University Law School

AI fabrications in legal filings grow in Oregon, US

The general counsel for the Oregon State Bar said fabricated cases and citations have become more common among lawyers and people representing themselves.

Lawsuit by Canadian news publishers against OpenAI gets green light to proceed in Ontario | CBC News

An Ontario court has decided a copyright lawsuit filed by Canadian news publishers against OpenAI will proceed in that province.

Home | Laws of UX

Laws of UX is a collection of best practices that designers can consider when building user interfaces.