Stanford Will Augment Its Study Finding that AI Legal Research Tools Hallucinate in 17% of Queries, As Some Raise Questions About the Results
Briefly

The study found that LexisNexis and Thomson Reuters AI legal research tools overstate the extent to which they are free of hallucinations, with both tools hallucinating more than 17% of the time.
There were substantial differences in responsiveness and accuracy between LexisNexis and Thomson Reuters systems, with LexisNexis delivering accurate responses 65% of the time and Thomson Reuters just 18%.
Read at LawSites
[
|
]