Incident 704: Study Highlights Persistent Hallucinations in Legal AI Systems

Description: Stanford University’s Human-Centered AI Institute (HAI) conducted a study in which they designed a "pre-registered dataset of over 200 open-ended legal queries" to test AI products by LexisNexis (creator of Lexis+ AI) and Thomson Reuters (creator of Westlaw AI-Assisted Research and Ask Practical Law AI). The researchers found that these legal models hallucinate in 1 out of 6 (or more) benchmarking queries.

Tools

New ReportNew ReportNew ResponseNew ResponseDiscoverDiscoverView HistoryView History

Incident Stats

Incident ID
704
Report Count
2
Incident Date
2024-05-23
Editors
Daniel Atherton
AI on Trial: Legal Models Hallucinate in 1 out of 6 (or More) Benchmarking Queries
hai.stanford.edu · 2024

Artificial intelligence (AI) tools are rapidly transforming the practice of law. Nearly three quarters of lawyers plan on using generative AI for their work, from sifting through mountains of case law to drafting contracts to reviewing docu…

We asked ChatGPT for legal advice—here are five reasons why you shouldn't
theconversation.com · 2024

At some point in your life, you are likely to need legal advice. A survey carried out in 2023 by the Law Society, the Legal Services Board and YouGov found that two-thirds of respondents had experienced a legal issue in the past four years.…

Variants

A "variant" is an incident that shares the same causative factors, produces similar harms, and involves the same intelligent systems as a known AI incident. Rather than index variants as entirely separate incidents, we list variations of incidents under the first similar incident submitted to the database. Unlike other submission types to the incident database, variants are not required to have reporting in evidence external to the Incident Database. Learn more from the research paper.

Similar Incidents

By textual similarity

Did our AI mess up? Flag the unrelated incidents