Câu 18: Databricks Certified Generative AI Engineer Associate

What is an effective method to preprocess prompts using custom code before sending them to an LLM?

1. A. Directly modify the LLM’s internal architecture to include preprocessing steps
2. B. It is better not to introduce custom code to preprocess prompts as the LLM has not been trained with examples of the preprocessed prompts
3. C. Rather than preprocessing prompts, it’s more effective to postprocess the LLM outputs to align the outputs to desired outcomes
4. D. Write a MLflow PyFunc model that has a separate function to process the prompts — đáp án hiện tại