1Z0-1127-25 Practice Question: Building LLM Applications with RAG and Vector Search
A company uses a RAG pipeline with OCI Data Science and Cohere embeddings. They notice that retrieval recall is low for domain-specific acronyms. What is the best practice to improve this?
⚠ Common exam trap
Oracle often tests the misconception that fine-tuning the embedding model is the default fix for retrieval issues, when in practice simpler preprocessing techniques like acronym expansion are more efficient and recommended for domain-specific vocabulary gaps.
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
✓
Expand acronyms to their full forms during document preprocessing and indexing.
Expanding acronyms to their full forms during document preprocessing and indexing ensures that the embedding model can map the acronym to its semantic meaning, improving retrieval recall for domain-specific terms. Cohere embeddings are trained on general text, so without expansion, acronyms like 'NLP' may not match queries for 'Natural Language Processing' in vector space. This preprocessing step directly addresses the root cause of low recall for acronyms.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Reduce the cosine similarity threshold in the vector search.
Why it's wrong here
May increase recall but also irrelevant results.
- ✓
Expand acronyms to their full forms during document preprocessing and indexing.
Why this is correct
Full forms improve semantic matching.
- ✗
Fine-tune the embedding model with domain-specific acronyms.
Why it's wrong here
Fine-tuning the embedding model primarily enhances its understanding of semantic relationships within a domain, improving how it represents related concepts. For domain-specific acronyms, the issue is often a lack of explicit lexical mapping or expansion, rather than the model's general semantic comprehension. The model needs to associate the acronym with its full form, which is typically addressed by pre-processing the text to expand acronyms or ensuring both forms are present in the retrieval index. Fine-tuning would be appropriate if the model struggled with the overall semantic similarity of domain-specific terms, not just their abbreviated forms.
- ✗
Increase the chunk size to include more context around acronyms.
Why it's wrong here
May not help if the acronym itself is not expanded.
Go deeper
Related to this question
About these practice questions
Courseiva writes every 1Z0-1127-25 question from scratch — 768 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
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.