QuestionQ70

VerifiedDesign AI-powered business solutions

A company has a generative AI model in Microsoft Foundry.

You need to evaluate the model output to assess the overall quality and coherence of generated responses. The evaluation must use GPT-4o as a judge and return a numeric score for each output.

Which metric type should you use?

Explanation

AI quality (AI assisted) metrics use a deployed GPT model as an LLM judge to score the overall quality and coherence of generated responses. AI quality (NLP) metrics are mathematical measurements that often require ground-truth data, while risk and safety metrics assess harmful content and groundedness measures a narrower factual-support dimension.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!