A New Turing Test for AI's Real-World Knowledge
A fresh set of benchmarks could help specialists better understand artificial intelligence.
Artificial intelligence (AI) models can perform as well as humans on law exams when answering multiple-choice, short-answer, and essay questions, as seen in a preprint at SSRN (2025). However, they struggle to perform real-world legal tasks.
Some lawyers have learnt that the hard way, and have been fined for filing AI-generated court briefs that misrepresented principles of law and cited non-existent cases.
Author: Chaudhri, principal scientist at Knowledge Systems Research in Sunnyvale, California.
Search author on: PubMed or Google Scholar.
Author's summary: New benchmarks are needed to assess AI's real-world knowledge.
More News
- How Discrimination and Stress Impact the Mental Health of Young Sexual Minority Men
- NewJeans loses Ador court battle to leave agency
- NBA head coach Tyronn Lue allegedly attended Chauncey Billups’ ‘rigged poker games’
- Disney Ended Doctor Who Partnership for These 3 Reasons
- Eala falls to Mboko to exit Hong Kong Open
- Emmy-Winner Chronicles Yankees Icon Joe Torre’s MLB Legacy On Screen
- CNN announces election night coverage plans, including All Access-only ‘livecast’
- We need a new Turing test to assess AI’s real-world knowledge
- Ahsoka Season 2 Gets Exciting Update From Rosario Dawson
- Baxter stock slides as Q3 sales come up short, guidance lowered