Courseiva
LLM FundamentalsmediumMultiple ChoiceObjective-mapped

1Z0-1127-25 LLM Fundamentals Practice Question

A data scientist is fine-tuning a Llama 2 model on a custom dataset for a summarization task. After fine-tuning, the model produces summaries that are too similar to the input text, often copying sentences verbatim. Which adjustment is MOST likely to reduce copying and improve abstractive summarization?

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

Increase the temperature to 0.8 and use top-p sampling

Increasing temperature (e.g., to 0.8) adds randomness to token selection, making the model less likely to choose the most probable tokens that lead to verbatim copying from the input. Top-p sampling further restricts the sampling pool to a cumulative probability mass, balancing diversity and coherence. In contrast, greedy decoding and beam search always select high-probability tokens, which encourages copying. Reducing context window may lose important information, not fix copying. Thus, higher temperature with top-p sampling is the best adjustment to promote abstractive summarization.

Answer analysis

Option-by-option breakdown

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

  • Increase the temperature to 0.8 and use top-p sampling

    Why this is correct

    Higher temperature flattens the probability distribution, making the model more likely to generate novel phrases rather than copying.

  • Switch to greedy decoding

    Why it's wrong here

    Greedy decoding always picks the highest probability token, which often leads to copying.

  • Increase the beam search width

    Why it's wrong here

    Beam search with higher width still favors high-probability sequences, potentially increasing copying.

  • Reduce the context window size

    Why it's wrong here

    Context window size does not directly affect copying; it limits input length.

About these practice questions

This 1Z0-1127-25 question is part of Courseiva's 768-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This 1Z0-1127-25 practice question is part of Courseiva's free Oracle certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the 1Z0-1127-25 exam.