A data scientist needs a metric that scores 1 when model output is character-for-character identical to the reference and 0 otherwise. Which metric should they configure in watsonx.governance?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Think of it this way: in real-world AI governance, exact match is exactly what teams reach for when they need to handle this scenario. Exact match is the correct metric for strict identity requirements. On the exam, remember that this falls squarely under the 4.0 Configure Evaluation and Monitoring domain.
Full explanation below image
Full Explanation
Exact match is the correct metric for strict identity requirements. It is a binary 0/1 metric with no partial credit, commonly used for fact-based question-answering tasks where the expected answer must be an exact string. The correct answer, "Exact match", directly addresses the scenario described because it aligns with the specific governance requirement in question. The incorrect options ("Cosine similarity", "Jaccard similarity", "ROUGE") may seem plausible but do not satisfy the core requirement. Understanding the distinction between these concepts is critical for IBM watsonx.governance implementations and is frequently tested in the 4.0 Configure Evaluation and Monitoring section of the certification exam.