A Generative AI 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…

Question

Options

• ASplit the LLM output by newline characters to truncate away the summarization explanation.
• BTune the chunk size of news articles or experiment with different embedding models.
• CRevisit their document ingestion logic, ensuring that the news articles are being ingested properly.
• DProvide few shot examples of desired output format to the system and/or user prompt.

• A
  6% (2)
• B
  3% (1)
• C
  15% (5)
• D
  76% (25)

Explanation

The problem is an output formatting issue - the LLM is producing correct content but appending unwanted meta-commentary. The most direct and reliable fix is few-shot prompting (option D): providing examples of ideal outputs (summary only, no explanation) teaches the model exactly what format is expected. Option A (splitting on newlines) is a brittle post-processing hack that will break on valid multi-line summaries. Option B (changing chunk size or embedding models) addresses retrieval quality, not output format. Option C (checking ingestion logic) addresses document content, not the LLM's response style.

No community discussion yet for this question.