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 [1], but they struggle to perform real-world legal tasks.
Some lawyers have learned the hard way, being 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 | Google Scholar
AI models can perform well on law exams, but struggle with real-world legal tasks.
Author's summary: New benchmarks are needed to assess AI's real-world knowledge.
More News
- Understanding the Different Types of Attic Insulation: Which One Works Best for Your Home? - GigWise
- Trump Goes Full Dictator With Bonkers Threat to Use Air Force and Navy in U.S. Cities
- Trump Serenaded With Anthem YMCA as He Lands in South Korea
- Record Job Cuts at Amazon and UPS. AI and Reorganization Changing the Face of Logistics
- Formula E's Women's Test is back: will it lead to real change on the grid?