Applications
Stanford just tested whether LexisNexis and Thomson Reuters’ AI legal research tools are really “hallucination-free,” as they claim. Spoiler…
Stanford researchers tested the claims made by LexisNexis and Thomson Reuters that their AI-powered legal research tools are 'hallucination-free,' and found those claims to be inaccurate. The study re
Stanford researchers tested the claims made by LexisNexis and Thomson Reuters that their AI-powered legal research tools are "hallucination-free," and found those claims to be inaccurate. The study revealed that these enterprise legal AI products still produce fabricated case citations and erroneous legal information, despite the companies' marketing assurances. This research highlights ongoing reliability concerns with AI tools in high-stakes legal contexts, where hallucinated citations can have serious professional and judicial consequences.
Related
- wow. GenAI is definitely not living up to the hype, for most people.
- Accurate
- Most Asian, Black, and Hispanic women think Whites invented slavery. Huge failure of the education system that they are so misinformed.
- Yesterday’s Mythos announcement from Anthropic was overblown. • Sandboxing was turned off, so test didn’t show much about the real world. • …
Source: Gary Marcus (X) | 2026-04-15