Databricks-GenAI-Assoc Application Development Practice Question
A team is building a retrieval-augmented generation application on Databricks and wants to reduce hallucination by improving the quality of retrieved context before it reaches the LLM. Which TWO techniques should they apply? (Choose two.)
⚠ Common exam trap
The trap here is equating more context or more randomness with better answers, when grounding quality depends on retrieving fewer, more relevant chunks.
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
✓
Apply a reranker model to the top-k retrieved chunks before passing them to the LLM.
Reranking retrieved candidates with a cross-encoder and improving chunking with overlap and metadata both raise the relevance of the context supplied to the LLM, which directly reduces hallucination. Raising temperature, stuffing the full corpus, and dropping semantic search all degrade grounding rather than improve it.
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 LLM temperature to encourage more diverse answers.
Why it's wrong here
Higher temperature increases randomness in generation, which worsens hallucination rather than reducing it. For grounded RAG answers, low temperature is preferred so the model sticks closely to retrieved evidence. This option moves in the opposite direction from the stated goal of improving context quality.
- ✓
Apply a reranker model to the top-k retrieved chunks before passing them to the LLM.
Why this is correct
A reranker scores retrieved candidates against the query with a cross-encoder, reordering them so the most relevant chunks appear first. This directly improves the precision of the context window and reduces the chance the LLM grounds its answer in loosely related passages. It is a standard post-retrieval step in Databricks RAG pipelines.
- ✗
Disable the Vector Search index and rely on keyword matching only.
Why it's wrong here
Replacing vector search with keyword-only matching removes semantic recall and typically degrades retrieval for paraphrased or conceptual queries. Hybrid search, which combines both, is stronger than either alone. Disabling the vector index contradicts the goal of improving retrieved context quality.
- ✓
Chunk documents with overlap and metadata so retrieval can filter by relevant attributes.
Why this is correct
Overlapping chunks preserve context across boundaries, and metadata enables filtered retrieval that narrows candidates to the relevant domain, date, or source. Together they raise the likelihood that the retrieved passages actually contain the answer. This is a foundational Databricks RAG practice for improving context precision before generation.
- ✗
Store the entire document corpus in the prompt for every request.
Why it's wrong here
Stuffing the whole corpus exceeds context limits, inflates cost, and paradoxically increases hallucination because irrelevant text distracts the model. Effective RAG depends on retrieving a small, highly relevant set of chunks, not on maximizing context volume. This approach defeats the purpose of retrieval.
About these practice questions
This Databricks-GenAI-Assoc question is part of Courseiva's 330-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 →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks 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 Databricks-GenAI-Assoc exam.