US Government Introduces New Benchmark for LLMs ⚡️

The National Institute of Standards and Technology (NIST) and relevant government agencies have introduced an official methodology and benchmark for the comprehensive assessment of the safety, reliability, and accuracy of large language models (LLMs).

The new standard focuses on:

• preventing hallucinations,
• resilience to jailbreaking,
• compliance with regulatory requirements when implementing artificial intelligence in both public and corporate sectors.