GCP Generative AI Leader Practice Question 68: Fine Tuning vs Prompting
Google Cloud Generative AI Leader · Test 7 · question 8 of 10
A legal team has spent months writing detailed prompt templates and few-shot examples to get a general-purpose model to draft contracts in the firm's exact house style and terminology. Despite extensive prompt tuning, the model still drifts from the required style and vocabulary on longer documents, and the firm has thousands of past contracts labeled by clause type available to use as training data.
What should the team do next?
Show answer and explanation
Answer:
Fine-tuning is the right move exactly when prompt engineering has been pushed as far as it can go and a sizable, high-quality labeled dataset exists: it adjusts the model's parameters directly so the desired style and terminology become baked into the model itself, rather than being re-explained in every prompt. The scenario describes both conditions, months of prompt tuning that still fall short, and thousands of labeled examples ready to use.
- B is wrong because the team has already invested heavily in prompt engineering and it has plateaued; repeating the same style guide more verbosely is unlikely to fix persistent drift on long documents. - C is wrong because swapping models without using the firm's available labeled data throws away the asset best suited to solving the exact problem, consistent house style. - D is wrong because raising temperature increases output randomness, which works against the goal of consistent, predictable house style rather than helping it.