Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Generative AI Leader practice bank has 2,191 more like it. Try 10 free: instant score, no account.
A customer service team wants to use a foundation model on Vertex AI to summarize incoming customer complaints and generate draft email responses. The team has no machine learning engineers, lacks a large labeled dataset, and needs to test and adjust instructions immediately with zero additional compute training costs.
Which approach should the team implement to achieve rapid results and refine outputs?
Pre-training from scratch is the initial phase of developing a base foundation model by training an entire neural network architecture on massive web-scale corpora containing hundreds of billions or trillions of tokens.
Reinforcement Learning from Human Feedback (RLHF) is an advanced post-training alignment method where human evaluators score model completions to train a reward model, which then optimizes the base model's behavior using reinforcement learning algorithms.
Prompt engineering (or prompt design) is the practice of structuring, refining, and optimizing the natural language inputs provided to a foundation model to guide it toward generating the desired output format, tone, and quality without modifying the model's underlying weights.
When resource availability is limited (no labeled training data and no ML engineering staff) and the primary objective is rapid iteration and immediate output adjustment, prompt engineering is the recommended first-line approach in Google Cloud.
Supervised model fine-tuning is the process of adapting a pre-trained foundation model by updating its internal parameters (weights) using a curated, high-quality dataset of paired inputs and desired outputs (examples).
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated