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

Question 1

A developer is using the Gemini API to build an application that generates SQL queries from natural language questions. The generated queries sometimes have syntax errors. They want to ensure the output is always valid SQL. Which approach is most effective?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Use a function call with a defined SQL query parameter and validate the output against a SQL parser.. Function calling lets the model return a structured object with a SQL query field, which the application can then parse and validate with a SQL parser. This creates a verification loop: if the query is invalid, the app can reject it or ask the model to retry. Combining structured output with deterministic validation is the most reliable way to guarantee syntactically correct SQL. Other options affect randomness or length but do not validate syntax.

Answer

Set the temperature to 0 to make the output deterministic.

Answer

Increase the max output tokens to give the model more room to correct itself.

Answer

Use controlled generation with a response schema that defines the SQL query structure.

Question 2

A hospital's patient-education team uses a generative AI model to produce discharge instructions. Clinicians report that the model sometimes omits the required warning about drug interactions even though the source notes contain it. They want to reliably increase the chance the warning appears in every relevant output. Which technique is most appropriate?

Accepted Answer

Add an explicit output requirement in the prompt that every discharge instruction must include a drug-interaction warning when the source notes mention one.. The failure is a missing mandatory element, so the fix must explicitly require that element in the output specification. A prompt-level output constraint makes inclusion conditional on the source notes and is immediately auditable. Sampling parameters, reasoning prompts, and fine-tuning influence randomness, reasoning depth, or base rates, but none reliably guarantees a specific required statement.

Answer

Fine-tune the model on a dataset of discharge instructions that contain interaction warnings.

Answer

Raise the top-k sampling value so more candidate tokens are considered.

Answer

Apply a chain-of-thought prompt asking the model to reason step by step before writing.

Question 3

A team is building a generative AI model for customer support. They notice the model often produces overly polite but unhelpful responses. Which technique would best improve response quality without sacrificing helpfulness?

Accepted Answer

Apply reinforcement learning from human feedback (RLHF). RLHF directly addresses the misalignment between the model's training objective (e.g., predicting the next token) and the desired outcome (helpful, not just polite). By using human feedback to train a reward model, the system learns to optimize for response quality and helpfulness, reducing sycophantic or overly polite but uninformative outputs.

Answer

Increase the amount of training data

Answer

Lower the top_k sampling value

Answer

Increase the temperature parameter

Question 4

A generative AI model for code generation sometimes produces syntactically incorrect code. The team wants to reduce syntax errors without retraining the entire model. Which approach is most effective?

Accepted Answer

Implement constrained decoding with grammar rules. Constrained decoding with grammar rules directly enforces the syntax of the target programming language during token generation, preventing the model from producing invalid constructs. This approach modifies the decoding process (e.g., using a context-free grammar or a formal syntax specification) to mask or forbid tokens that would lead to a syntax error, without altering the underlying model weights. It is the most effective method because it guarantees syntactically correct output at generation time, rather than relying on post-hoc fixes or probabilistic adjustments.

Answer

Run a syntax checker after generation and regenerate

Answer

Add a system prompt that instructs the model to produce valid code

Answer

Increase beam search width

Question 5

A company uses a text-to-image model to generate marketing visuals. The outputs often contain distorted human faces. Which technique is most likely to improve face generation?

Accepted Answer

Fine-tune the model on a curated dataset of human faces. Fine-tuning the model on a high-quality dataset of human faces directly addresses the distortion issue by specializing the model for face generation. Option B (increasing output resolution) may improve overall image sharpness but does not specifically correct face distortions. Option C (increasing inference steps) can enhance image coherence but is not targeted at face quality. Option D (reducing classifier-free guidance scale) decreases prompt adherence, which could actually worsen face generation rather than improve it.

Answer

Increase the output resolution

Answer

Increase the number of inference steps

Answer

Reduce the classifier-free guidance scale

Question 6

A team is deploying a large language model for legal document summarization. They find the model occasionally omits critical legal clauses. Which improvement technique would be most effective?

Accepted Answer

Design a prompt that explicitly lists required sections. The most effective technique is to design a prompt that explicitly lists the required sections. This is a form of prompt engineering that directly addresses the omission issue by instructing the model to include all specified clauses, leveraging the model's instruction-following capability. It is immediate, low-cost, and does not require retraining or altering sampling parameters. By enumerating the sections, the model is guided to cover each one, reducing the chance of missing critical content.

Answer

Increase the top_p value to 1.0

Answer

Fine-tune the model on legal summaries

Answer

Lower the temperature to 0.1

Question 7

A generative AI model for chatbot responses sometimes produces toxic language. The team wants to reduce toxicity without significantly affecting the model's helpfulness. Which approach is best?

Accepted Answer

Fine-tune with a dataset of non-toxic responses and use RLHF. Fine-tuning with a curated dataset of non-toxic responses directly adjusts the model's weights to reduce the likelihood of generating toxic language, while RLHF (Reinforcement Learning from Human Feedback) further aligns the model with human preferences for helpfulness and safety. This combined approach addresses the root cause of toxicity in the model's behavior without the blunt trade-offs of other methods, preserving the model's utility.

Answer

Increase the temperature parameter

Answer

Reduce the maximum output tokens

Answer

Apply a toxicity classifier as a post-processing filter

Question 8

A team notices their text generation model repeats phrases excessively. Which technique would most directly reduce repetition?

Accepted Answer

Apply a repetition penalty of 1.2. Applying a repetition penalty directly penalizes the model for generating tokens that have already appeared in the output, reducing the probability of repeated phrases. Unlike sampling or beam search adjustments, this technique explicitly targets the repetition issue by scaling down the logits of previously generated tokens during decoding.

Answer

Use beam search with a beam width of 5

Answer

Increase top_k to 100

Answer

Lower temperature to 0.5

Question 9

A company uses a generative model to produce product descriptions. The descriptions are factually inconsistent with the product specs. Which technique would best ensure factual accuracy?

Accepted Answer

Implement retrieval-augmented generation (RAG) with product database. Retrieval-augmented generation (RAG) is the best technique because it dynamically retrieves relevant, up-to-date product specifications from a trusted database at inference time, grounding the model's output in verified facts. This directly addresses factual inconsistency by ensuring the generated description is based on authoritative source data rather than relying solely on the model's parametric memory.

Answer

Enhance the system prompt with product details

Answer

Lower the temperature to 0.0

Answer

Fine-tune the model on product descriptions

Question 10

A team is fine-tuning a large language model for medical advice. Which TWO techniques are most effective for improving the safety and reliability of the model's outputs?

Accepted Answer

Constitutional AI. Constitutional AI (A) is correct because it embeds a set of ethical principles directly into the model's training process, allowing the model to self-critique and revise its outputs to avoid harmful or unsafe medical advice. This technique proactively enforces safety constraints without requiring extensive human labeling, making it highly effective for high-stakes domains like healthcare.

Answer

Lowering the temperature to 0.0

Answer

Increasing training data size

Answer

Increasing top_p to 1.0

Question 11

A team wants to reduce hallucinations in a question-answering model. Which THREE techniques should they consider?

Accepted Answer

Fine-tune the model on a curated factual dataset. Fine-tuning on a curated factual dataset directly adjusts the model's weights to prioritize accurate, domain-specific knowledge, reducing the likelihood of generating unsupported or hallucinated content. This technique anchors the model's output in verified data, making it more reliable for question-answering tasks.

Answer

Reduce the number of tokens in output

Answer

Increase the temperature parameter

Question 12

Which TWO techniques are commonly used to control the style and tone of a generative model's output?

Accepted Answer

Fine-tuning on a dataset with desired style. Fine-tuning on a dataset that embodies the desired style directly adjusts the model's weights, making it consistently produce outputs with that specific tone and style. This is a fundamental technique for customizing generative models, as it teaches the model the exact patterns, vocabulary, and stylistic nuances present in the training data.

Answer

Adjusting the temperature

Answer

Modifying the top_k value

Answer

Changing the top_p value

Question 13

Refer to the exhibit. The team changed the generation parameters to reduce output variability. However, summaries now often repeat the same phrases. Which parameter change is most likely causing the repetition?

Accepted Answer

Reducing temperature from 0.7 to 0.2. Reducing temperature from 0.7 to 0.2 makes the model's token selection much more deterministic, favoring the highest-probability tokens. This low-entropy sampling often causes the model to repeat the same phrases across summaries because it consistently picks the most likely continuation.

Answer

Reducing top_p from 0.95 to 0.85

Answer

Using the same model text-bison@002

Answer

Reducing top_k from 40 to 10

Question 14

Refer to the exhibit. The endpoint is experiencing high latency during traffic spikes. The team wants to improve response time by reducing queueing. Which change to the configuration would be most effective?

Accepted Answer

Increase maxReplicaCount to 10. Increasing maxReplicaCount to 10 allows the autoscaler to provision more replicas during traffic spikes, distributing the incoming requests across additional endpoints. This directly reduces queueing at each replica because the load is spread over more instances, lowering per-instance latency. The change targets the root cause—insufficient capacity to handle peak load—rather than adjusting thresholds or model versions.

Answer

Decrease minReplicaCount to 0

Answer

Change the model version to '2'

Answer

Decrease the target value in autoscaling metric to 50

Question 15

A data science team is fine-tuning a large language model using Vertex AI to generate marketing copy. They notice that the generated text is often repetitive and lacks creativity. Which technique should they apply to improve output diversity?

Accepted Answer

Increase the temperature parameter to 0.9.. Increasing the temperature parameter to 0.9 raises the randomness of the probability distribution over tokens, allowing less likely tokens to be selected. This directly counteracts repetitive output by encouraging the model to explore more diverse word choices, which is a standard technique for improving creativity in text generation.

Answer

Decrease the beam search width to 1.

Answer

Decrease the top-k sampling threshold.

Answer

Add more examples of repetitive text to the training dataset.