AI Consortium Plans Toolkit to Rate AI Model Safety
ID: 6f6c61ce-8122-5af3-bf5b-950a54a6d056
STIX ID: report--6f6c61ce-8122-5af3-bf5b-950a54a6d056
Feed Name: Dark Reading
MLCommons has introduced an AI Safety benchmark to stress-test LLMs with adversarial prompts and assign public safety ratings (L, ML, M, MH, H) for risks including hate speech, child safety, exploitation, IP violations, and defamation; v0.5 tested anonymized models and the group aims to release a stable v1.0 by October 31 so vendors and organizations can evaluate and improve model safety.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.