AB-100 Certification Practice Question #72

Question

A company has a Microsoft Foundry generative AI model.

You need to evaluate the model's output to measure 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 type of metric should you use?

Accepted Answer

AI quality (AI assisted) metrics are designed for exactly this use case: using a capable LLM (GPT-4o in this case) as a judge to evaluate the quality, coherence, relevance, and helpfulness of generated responses, returning a numeric score for each output. NLP metrics (A) don't use an LLM judge. Risk and safety (B) focuses on harmful content. Groundedness (C) is a specific factual-accuracy metric. Only AI quality (AI assisted) matches all three stated criteria: quality/coherence measurement, GPT-4o as judge, and numeric scores.

More AB-100 practice questions