Generative AI Leader Techniques to Improve Generative AI Model Output Practice Test 2 — 15 Questions

Question 1

A team is using a pre-trained language model to summarize legal documents. They find that summaries often miss key dates and parties involved. Which technique would most effectively improve factual accuracy?

Accepted Answer

Fine-tune the model on a dataset of legal summaries with annotated key entities.. Fine-tuning on a dataset of legal summaries with annotated key entities directly teaches the model to recognize and reproduce critical factual elements like dates and parties. This supervised learning approach adjusts the model's weights to prioritize entity extraction and accurate generation, which is the most effective method for improving factual accuracy in domain-specific tasks.

Answer

Use top-p sampling with a low p value.

Answer

Increase the temperature parameter.

Answer

Use chain-of-thought prompting.

Question 2

A company is deploying a generative AI model for customer support. They want to reduce hallucinations while maintaining fluency. They have a large dataset of previous support conversations. Which strategy should they prioritize?

Accepted Answer

Implement retrieval-augmented generation (RAG) using the conversation dataset as a knowledge base.. Retrieval-augmented generation (RAG) directly addresses hallucinations by grounding the model's responses in factual, retrieved data from the conversation dataset. This approach allows the model to generate fluent, contextually relevant answers while reducing the risk of inventing information, as it retrieves actual support interactions as evidence before generating a response.

Answer

Increase the beam search width to 10.

Answer

Fine-tune the model on the conversation dataset.

Answer

Set the temperature to 0.1.

Question 3

A developer is using Vertex AI Studio to test prompts for a text generation model. They want the model to follow a specific output format (JSON). Which prompt engineering approach is most effective?

Accepted Answer

Include a few-shot example of the exact JSON format in the prompt.. Option B is correct because including a few-shot example of the exact JSON format in the prompt provides the model with a concrete pattern to follow, which is the most reliable method for enforcing structured output in generative models. Few-shot prompting leverages in-context learning, where the model uses the provided example to infer the desired schema and formatting rules, reducing ambiguity and improving adherence to the specified JSON structure.

Answer

Set stop sequences to '}'.

Answer

Set the system instruction to 'Always output JSON.'

Answer

Set temperature to 0 to make output deterministic.

Question 4

Which TWO techniques can help improve the factual accuracy of a language model's outputs? (Choose two.)

Accepted Answer

Fine-tune on a domain-specific curated dataset.. Fine-tuning on a domain-specific curated dataset (C) directly adjusts the model's weights using high-quality, verified examples, teaching it to produce factually correct outputs for that domain. This reduces hallucinations by grounding the model in accurate, relevant data rather than relying solely on its pre-training distribution.

Answer

Decrease the max output tokens.

Answer

Increase the temperature parameter.

Answer

Use top-k random sampling.

Question 5

Which THREE approaches are effective for reducing bias in generative model outputs? (Choose three.)

Accepted Answer

Use a balanced training dataset.. Option C is correct because a balanced training dataset reduces the risk of the model learning spurious correlations or skewed distributions that lead to biased outputs. By ensuring that all demographic groups, topics, or perspectives are represented proportionally, the model's learned probability distribution is less likely to favor one group over another, directly mitigating representation bias at the data level.

Answer

Set temperature to a very high value.

Answer

Use adversarial training.

Question 6

A healthcare company is using a fine-tuned version of PaLM 2 on Vertex AI to generate clinical notes from doctor-patient conversations. The model was fine-tuned on a dataset of 10,000 de-identified transcripts and corresponding notes. During testing, the generated notes are grammatically correct and well-structured, but they often contain subtle inaccuracies: for example, they might mention a medication that was not discussed, or omit a key symptom. The team has already tried increasing the training epochs and adjusting learning rates, with minimal improvement. They need a solution that can be implemented quickly to improve factual accuracy without retraining the entire model. The team has access to a large archive of verified clinical notes and a small set of recent conversation-to-note pairs that have been manually reviewed and corrected. The inference pipeline currently uses a single call to the model with the conversation transcript as input. What should the team do?

Accepted Answer

Implement retrieval-augmented generation (RAG) by retrieving similar verified notes from the archive and providing them as context in the prompt.. Option A is correct because retrieval-augmented generation (RAG) directly addresses the core issue of factual inaccuracy without retraining. By retrieving verified clinical notes similar to the current conversation from the archive and injecting them as context in the prompt, the model gains access to ground-truth examples that anchor its output to factual details. This approach leverages the team's existing archive and small set of corrected pairs to provide relevant, accurate context, improving precision without modifying the model's weights.

Answer

Decrease the temperature to 0.1 to reduce randomness and force the model to stick to the input.

Answer

Use prompt engineering to instruct the model to only include information explicitly mentioned in the conversation.

Answer

Add a human-in-the-loop step to review and correct every generated note before use.

Question 7

A media company is using Vertex AI's Imagen model to generate images for marketing campaigns. They have a set of prompts that describe desired scenes, but the generated images often contain artifacts such as distorted faces or unnatural lighting. The team has tried varying the prompt wording but the issues persist. They are using the default parameters (no modifications). They have a budget for additional compute resources and want to improve image quality without switching to a more expensive model. The team has access to a small set of high-quality images in the same style as their target outputs. What should the team do?

Accepted Answer

Fine-tune the Imagen model on the small set of high-quality images to improve output quality.. Option B is correct because fine-tuning Imagen on the small set of high-quality images can improve the model's ability to generate images with fewer artifacts and better style consistency. Option A is wrong because increasing the number of images generated does not improve quality per image. Option C is wrong because adjusting guidance scale without fine-tuning may not address the specific artifacts. Option D is wrong because using a different prompt style may help but the team already tried varying wording; the issue is likely the model's lack of familiarity with the desired quality.

Answer

Increase the guidance scale parameter to make the model follow prompts more closely.

Answer

Use a more detailed prompt style with negative prompts to avoid artifacts.

Answer

Increase the number of images generated per prompt and manually select the best ones.

Question 8

You are a Generative AI architect at a large financial services firm. The firm has deployed a custom large language model (LLM) fine-tuned on proprietary financial reports to assist analysts in generating quarterly earnings summaries. The model is hosted on Vertex AI using a dedicated endpoint with autoscaling enabled. Recently, the model's output has exhibited two issues: (1) occasional factual inaccuracies about specific financial figures, and (2) a tendency to produce overly verbose and repetitive text in the summaries, sometimes exceeding the desired length of 200 words. The team has already tried adjusting the temperature parameter from 0.7 to 0.2 and increased the top-k sampling from 40 to 50, but the problems persist. The model's training data includes over 10,000 financial reports, and the fine-tuning process used low-rank adaptation (LoRA) with rank 16. The production environment uses a batch size of 1 for inference. You need to recommend a course of action that most directly addresses both the factual accuracy and verbosity issues without requiring a full retraining of the model. Which approach should you take?

Accepted Answer

Implement a retrieval-augmented generation (RAG) pipeline that queries a vector database of verified financial data, and apply constrained decoding with a maximum token limit and a repetition penalty.. Option B is correct because it directly addresses both issues without retraining. A RAG pipeline grounds the model's outputs in verified financial data, eliminating factual inaccuracies. Constrained decoding with a maximum token limit and repetition penalty directly curbs verbosity and repetition, which temperature and top-k adjustments failed to fix.

Answer

Increase the LoRA rank to 32 and fine-tune the model for additional epochs on a curated subset of reports that focus on concise and accurate summaries.

Answer

Switch to a larger pre-trained model (e.g., PaLM 2 or GPT-4) and use the same fine-tuning data with higher rank LoRA to improve capability, then rely on the larger model's inherent accuracy.

Answer

Experiment with higher temperature (e.g., 0.9) and lower top-k (e.g., 20) to encourage more diverse and concise outputs, and add a post-processing step to truncate summaries to 200 words.

Question 9

A company notices that their AI chatbot occasionally generates incorrect information. Which technique can best reduce hallucinations without retraining?

Accepted Answer

Use system instructions to constrain the model to only answer from provided context. Using system instructions to constrain the model to the provided context directly reduces fabrication. Increasing temperature or setting top_p low would not specifically target hallucinations.

Answer

Use a longer system prompt without examples

Answer

Set top_p to 0.1

Answer

Increase temperature to 0.9

Question 10

A team wants to improve the factual accuracy of their chatbot responses regarding internal company policies. What is the most effective approach?

Accepted Answer

Use RAG with Vertex AI Search indexing the policies. RAG with Vertex AI Search retrieves current policy documents, providing authoritative context. Fine-tuning may not capture frequent updates, and other options do not integrate live knowledge.

Answer

Use few-shot prompting with example Q&A pairs

Answer

Increase the model's maximum tokens

Answer

Fine-tune the model on policy documents

Question 11

A real-time customer support chatbot using Gemini is experiencing high latency. The team must maintain response quality while improving speed. Which technique should they implement?

Accepted Answer

Use context caching for frequent queries. Context caching reuses context from common intents, reducing processing time without sacrificing quality. Temperature changes or larger models would not help latency or quality.

Answer

Switch to a larger model

Answer

Increase the batch size

Answer

Decrease the temperature

Question 12

A marketing company wants to fine-tune a generative AI model to adopt a specific brand voice. Which tuning method is most appropriate?

Accepted Answer

Supervised fine-tuning with labeled examples of the brand voice. Supervised fine-tuning with labeled examples directly teaches the desired style. RLHF is for broader alignment, and grounding or prompt engineering are not as precise for tone.

Answer

RLHF with general user feedback

Answer

Grounding with external knowledge base

Answer

Prompt engineering with system instructions

Question 13

Despite applying safety filters, a generative AI model still produces toxic outputs in some cases. Which additional technique should be applied?

Accepted Answer

Use RLHF with human feedback to reduce toxicity. RLHF using human feedback to penalize toxic responses directly reduces such outputs. Other options either weaken safety or do not target toxicity specifically.

Answer

Add more examples of toxic content to training

Answer

Increase the filter threshold

Answer

Decrease the model's temperature

Question 14

A model generates responses that frequently repeat phrases or words. Which parameter adjustment is most likely to fix this?

Accepted Answer

Increase repetition penalty. Increasing the repetition penalty directly discourages the model from selecting tokens that have already appeared in the generated sequence, thereby reducing repetitive phrases or words. This parameter works by subtracting a fixed penalty from the logits of previously generated tokens before applying the softmax function, making them less likely to be chosen again.

Answer

Increase top_k

Answer

Increase temperature

Answer

Increase max output tokens

Question 15

To ensure that a generative AI model uses the most current information from the web for answering user queries, which Vertex AI feature should be enabled?

Accepted Answer

Grounding with Google Search. Grounding with Google Search is the correct feature because it enables the model to retrieve and reference real-time information from the web, ensuring responses are based on the most current data available. This is achieved by integrating Google Search results directly into the model's generation process, allowing it to cite live sources and reduce hallucinations from outdated training data.

Answer

Safety filters

Answer

Context caching

Answer

Model tuning