hardMultiple Choice
Generative AI Leader Practice Question: A startup is building a generative AI legal…
A startup is building a generative AI legal document assistant for small law firms. They want to ensure that the model's outputs are accurate and can be traced back to specific legal statutes. Which approach best supports this requirement?
⚠ Common exam trap
Google often tests the misconception that larger models or fine-tuning alone can guarantee factual accuracy and traceability, when in fact retrieval-augmented generation is required for verifiable, source-grounded outputs.
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
✓
Use a RAG architecture that retrieves relevant statutes and includes them as citations in the model's response
Retrieval-Augmented Generation (RAG) architecture retrieves specific legal statutes from a trusted external knowledge base and includes them as citations in the model's response. This ensures both accuracy (by grounding outputs in verifiable sources) and traceability (by providing direct references to the statutes used). Fine-tuning alone cannot guarantee that the model will cite specific statutes correctly, as it may hallucinate or misremember legal references.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Fine-tune the model on a large corpus of legal documents
Why it's wrong here
Fine-tuning adjusts model weights for style and domain fluency but does not attach citations to statutes, so outputs remain untraceable. It is tempting because domain training improves legal terminology, and would be correct if the requirement were tone or vocabulary rather than verifiable source attribution.
- ✗
Apply a high temperature setting to encourage diverse outputs
Why it's wrong here
High temperature increases sampling randomness, producing varied wording and raising hallucination risk, which undermines both accuracy and traceability. It is tempting because diversity suits brainstorming or creative drafting, and would be correct if the goal were generating varied options rather than statute-cited accuracy.
- ✗
Use a model larger than 70B parameters
Why it's wrong here
Parameter count affects general capability, not provenance; a larger model still generates unsourced text and may hallucinate statutes. It is tempting because bigger models often perform better on reasoning benchmarks, and would be correct if the requirement were raw capability rather than traceable citation of legal sources.
- ✓
Use a RAG architecture that retrieves relevant statutes and includes them as citations in the model's response
Why this is correct
RAG retrieves the relevant statutes from an external store and injects them into the prompt, so each answer can cite the specific source it drew on. This grounds outputs in verifiable legal text, satisfying the traceability and accuracy requirement.
Go deeper
Related to this question
About these practice questions
One of 1,008 original Generative AI Leader practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader exam.