GenAI & LLM Engineering Objective Questions and Answers

This GenAI & LLM engineering quiz contains carefully curated objective questions with correct answers and clear explanations. It is designed for developers and ML engineers to test your skills in building, optimizing, evaluating, and deploying LLM-powered applications.

Practice GenAI & LLM Engineering MCQs with Detailed Explanations

Answer at least 12 questions to submit.

1

Which technique is most suitable to reduce hallucinations in LLM-based applications that answer from private documents?

Medium
2

What is the primary role of embeddings in GenAI systems?

Easy
3

Which factor most directly impacts LLM inference latency in production?

Medium
4

What is a key benefit of using quantization for LLM deployment?

Medium
5

Which decoding strategy is most likely to increase output diversity but also hallucinations?

Medium
6

In a RAG pipeline, what is the main purpose of chunking documents?

Medium
7

Which metric is most appropriate for evaluating retrieval quality in a vector search system?

Hard
8

What is the main advantage of parameter-efficient fine-tuning (PEFT) methods like LoRA?

Medium
9

Which approach best mitigates prompt injection attacks in production systems?

Hard
10

What is the main purpose of a system prompt in LLM applications?

Easy
11

Which architecture component enables LLMs to capture long-range dependencies?

Medium
12

What is the primary drawback of increasing context window size?

Medium
13

Which technique helps prevent data leakage from training data in deployed LLMs?

Hard
14

What is the key role of rerankers in a RAG pipeline?

Medium
15

Which failure mode occurs when the LLM answers confidently with incorrect facts?

Easy