Databricks Certified Generative AI Engineer Associate — Question 36

A Generative Al Engineer is creating an LLM system that will retrieve news articles from the year 1918 and related to a user's query and summarize them. The engineer has noticed that the summaries are generated well but often also include an explanation of how the summary was generated, which is undesirable.
Which change could the Generative Al Engineer perform to mitigate this issue?

Answer options

• A. Split the LLM output by newline characters to truncate away the summarization explanation.
• B. Tune the chunk size of news articles or experiment with different embedding models.
• C. Revisit their document ingestion logic, ensuring that the news articles are being ingested properly.
• D. Provide few shot examples of desired output format to the system and/or user prompt.

Correct answer: D

Explanation

The correct answer is D because providing few-shot examples helps the model understand the expected format of the output, reducing unwanted explanations. Option A would only remove parts of the output but not address the root cause. Option B focuses on configurations that may not directly influence the summarization style. Option C involves the ingestion process, which is not the source of the summarization issue.