LLM Fundamentals →hardMultiple SelectObjective-mapped

1Z0-1127-25 LLM Fundamentals Practice Question

An organization is deploying an LLM for document question answering. They want to reduce hallucinations and ensure answers are grounded in provided documents. Which THREE techniques should they implement? (Choose three.)

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Fine-tune the model on a corpus of in-domain documents

RAG retrieves relevant document chunks and conditions the generation on them, reducing hallucination. Fine-tuning on the document domain can improve grounding. Using a lower temperature (closer to 0) makes the model more deterministic and less likely to fabricate. Higher temperature increases hallucination risk, and longer context window alone does not guarantee grounding.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Use a longer context window to include more document text
Why it's wrong here
A longer context window alone does not ensure the model uses the information correctly; it can still hallucinate.
✓
Fine-tune the model on a corpus of in-domain documents
Why this is correct
Fine-tuning on relevant documents improves the model's knowledge and can reduce hallucination.
✓
Set a low temperature (e.g., 0.1) for sampling
Why this is correct
Low temperature makes the model more deterministic and less likely to generate ungrounded content.
✗
Set a high temperature (e.g., 1.5) for sampling
Why it's wrong here
Higher temperature increases randomness and the likelihood of hallucination.
✓
Use Retrieval-Augmented Generation (RAG)
Why this is correct
RAG grounds the generation in retrieved document chunks, reducing hallucination.

Go deeper

1Z0-1127-25 LLM Fundamentals Practice Question

Why each option matters

Option-by-option breakdown

Related to this question