Techniques to Improve Generative AI Model Output

A healthcare startup uses a generative model fine-tuned on general medical literature to provide preliminary diagnostic suggestions from patient text. The model frequently misses rare diseases and sometimes suggests common conditions that are unlikely given the symptoms. The startup has a curated dataset of rare disease case reports and wants to improve the model’s sensitivity to rare conditions without sacrificing overall accuracy. They cannot afford to retrain the entire model from scratch. The model is deployed on Vertex AI Prediction with low latency requirement. Which approach should they take?

A retail bank uses a generative AI assistant to answer customer questions about account policies. Compliance requires that every response cite the specific internal policy document section it used. Which approach best enforces this requirement?

A data scientist is using Vertex AI generative AI studio to create a chatbot. The chatbot gives inconsistent answers to similar questions. Which parameter should they adjust to make responses more consistent?

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?

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

A financial services firm is using a generative AI model to answer customer queries about account balances. The model sometimes provides outdated information because it relies on its training data. The firm wants to ensure the model always uses the most current account data. Which technique should they use?

A research team is using a large language model to analyze medical research papers and generate summaries. They need to minimize hallucinations while retaining key details. They have access to a curated database of paper abstracts. Which approach is best?

A large e-commerce company deploys a generative AI chatbot on Vertex AI for customer service. The chatbot is powered by a fine-tuned model on the company's historical support tickets. Despite high accuracy on training topics, the chatbot frequently gives irrelevant or off-topic answers when customers ask about new products or promotions. The company maintains a comprehensive product catalog and a knowledge base of current promotions. The chatbot's prompts include a system instruction to 'Answer based on your knowledge' and no other retrieval mechanism. The response time requirement is under 3 seconds. Which course of action should the team take?

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

A retail bank uses a Gemini model on Vertex AI to answer customer questions about its mortgage products. Testers report that the model sometimes invents interest rates that do not exist in the bank's rate sheet. The team wants the model to ground its answers only in an approved corpus of product documents and cite the passages it used. Which approach should they implement?

A team is fine-tuning a model for a legal document summarization task. They need to ensure high accuracy and avoid hallucinations. Which TWO approaches should they combine? (Choose two.)

An e-commerce company fine-tunes a model on customer reviews to generate product feedback summaries. They want to ensure the model does not reproduce toxic language from the training data. Besides filtering the training data, which additional technique is most effective at inference time?

A user provides a long document as context for a question-answering task, but the model outputs irrelevant answers. What is the most likely cause?

A social media company uses a generative AI model to moderate user posts. The model occasionally allows offensive content. Which safety technique should be implemented?

A company is deploying a generative AI system that generates customer-facing emails. The system must ensure outputs are not toxic, biased, or harmful. Which TWO techniques are most effective for reducing toxicity in model outputs without significantly affecting performance?

A developer is tuning a text-generation model for creative writing. They want the outputs to be more diverse and less repetitive. Which THREE parameters/changes can help? (Choose three.)

A media company uses Gemini models on Vertex AI to draft news briefs from long press releases. Editors report that drafts sometimes invent quotes and statistics that do not appear in the source. The team wants to reduce these fabrications while keeping the model's fluent writing. Which TWO techniques should they apply? (Choose two.)

A healthcare company is using a generative AI model to produce patient education materials. They want to ensure the output is accurate, avoids harmful advice, and adheres to medical guidelines. Which TWO techniques should they implement to improve the safety and reliability of the model's output? (Choose two.)

A data scientist fine-tunes a model on a small proprietary dataset. After fine-tuning, the model repeats training examples verbatim. What is the most effective mitigation?

A healthcare analytics team uses Gemini on Vertex AI to extract structured data from clinical notes. The model occasionally outputs invalid JSON, breaking downstream processing. The team wants to enforce a strict output schema. Which approach should they use?

Which TWO methods are most effective for improving factual accuracy in a language model's responses? (Choose two.)

A company uses a generative AI model to generate product descriptions. They notice variations in style and length across products. How can they enforce consistent formatting?

To improve factuality in generative AI, which is the best approach?

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?

A research team uses a generative AI model to answer questions about internal technical documents. The model sometimes provides outdated information because it relies on its pretrained knowledge instead of the latest documents. The team wants the answers to be based on the current document set. Which technique should they implement?

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?

A product team is using a generative AI model to summarize customer feedback from multiple sources. The summaries are sometimes missing key themes or including irrelevant details. The team wants to improve the quality of the summaries without retraining the model. (Choose two.)

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?

A team is using Vertex AI Pipelines to deploy a generative AI model for real-time inference. The model sometimes generates harmful content. They want to implement a safety filter that checks the output before returning it to the user, but they need to minimize latency. Which approach best balances safety and performance?

A data science team is building a document question-answering assistant on Vertex AI. Users report that answers are sometimes fabricated when the retrieved passages do not contain the answer. Which TWO techniques should the team apply to reduce hallucinations? (Choose two.)

A developer uses the Gemini API to summarize long articles. The summaries often miss key points from the end of the article. Which technique specifically addresses this length-based loss of information?

A financial services firm uses a generative AI model on Vertex AI to answer employees' HR policy questions. The model sometimes invents policy details. The firm wants answers grounded in the official HR handbook and needs to cite the source section. Which solution should they implement?

A company uses a generative AI model to answer customer queries. The model sometimes returns outdated information. Which technique should they apply to ensure responses rely on current data?

A developer is using the Gemini API to generate creative product taglines. The taglines are often bland and uncreative. The developer wants more variety and novelty in the outputs. Which parameter adjustment would most effectively increase the diversity of the generated taglines?

A healthcare company is using a generative AI model to draft patient education materials. The model sometimes includes outdated medical advice. The team wants to ensure the content reflects the latest clinical guidelines. They have a database of current guidelines and want to integrate it into the generation process without retraining the model. Which approach should they use?

Which TWO are advantages of using Retrieval-Augmented Generation (RAG) over fine-tuning?

A developer is using the Gemini API to generate creative marketing copy. They want the output to be more diverse and unexpected. Which parameter should they increase?

Refer to the exhibit. A Vertex AI endpoint configured with the above deployment is returning HTTP 429 (Too Many Requests) errors during peak traffic. The current CPU utilization reaches 80% consistently. What should the team adjust to resolve this?

A media company uses a generative AI model to draft weekly newsletter articles from bullet points. The drafts are factually correct but read as terse and disjointed. Editors want smoother narrative flow without changing the underlying facts. Which technique should they apply first to improve the output?

A software company is using a large language model to generate code snippets from natural language descriptions. The generated code often contains syntax errors or uses deprecated functions. The team wants to improve the correctness of the code. Which technique should they use?

A financial services firm uses a generative AI model to summarize quarterly earnings calls. The summaries must consistently follow a strict format: an executive summary, key financial metrics, and forward-looking statements. The model sometimes omits sections or changes the order. Which technique should they use to enforce the structure?

A developer uses a code generation model to write Python functions. The output frequently contains syntax errors due to incorrect braces and indentation. Which technique should be used to produce syntactically valid code?

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?

A media company uses Gemini on Vertex AI to generate short news summaries from long articles. The summaries frequently miss key facts and sometimes include details not in the source. The team wants to improve factual grounding and coverage without retraining the model. (Choose two.)

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?

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?

A company is using a generative AI model to generate product descriptions. They notice the outputs often include factual inaccuracies about product specifications. Which technique would best address this issue without modifying the model's architecture?

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?

A law firm uses a generative model to analyze contracts and extract key clauses. The model often outputs irrelevant clauses or misses important ones. They want to improve the relevance of the outputs without retraining the entire model. Which approach is best?

A marketing team is using a text generation model to create ad copy. They notice that the model's output is often bland and lacks creativity. They want to increase the diversity of the generated text while keeping it relevant. Which parameter should they adjust?

A financial services firm is deploying a generative AI model to answer customer questions about investment products. They want to ensure the model's responses are compliant with regulations and do not provide personalized financial advice. Which TWO techniques can help achieve this? (Choose two.)

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?

Which TWO techniques effectively reduce bias in generative model outputs? (Choose two.)

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?

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?

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

Which TWO techniques are most effective for improving the quality of a generative AI model's output when summarizing complex documents?

A marketing team uses a text generation model to create ad copy. They want the output to be more diverse and creative, exploring unusual angles. Which parameter should they adjust?

Refer to the exhibit. A user wants formal translations from a generative AI model, but the model outputs informal style inconsistently. Which prompt engineering technique would best ensure consistent formal translations?

A company uses a text-to-image model to generate marketing visuals. The results often misinterpret the prompt, e.g., 'a red car' generates a blue car. Which technique should they try first to align the output with the prompt?

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?

A marketing team uses a generative AI model on Vertex AI to create ad copy variations. The outputs are often too random and include off-brand phrases. They want to reduce randomness while still allowing some creativity. Which parameter should they adjust?

A retail analytics team uses a Gemini model to answer questions over a large product catalog stored in BigQuery. Answers are sometimes outdated because the model relies on its training data. They want responses to reflect the latest catalog rows and cite the source table. Which technique should they implement?

A team is building a customer support assistant on Vertex AI using a foundation model. They notice the model occasionally invents policy details that don't exist in their internal documentation. They want the model to ground its answers in the company's knowledge base and provide citations. Which approach should they use?

An enterprise uses a fine-tuned PaLM 2 model for code generation. They want to ensure the generated code passes security audits. Which combination of techniques would be most effective?

A marketing team uses a generative AI model to create short social media posts from long product briefs. The posts frequently include made-up statistics and product claims that are not in the brief. The team wants to reduce these unsupported statements without retraining the model. Which technique should they apply first?

A team is using a language model for customer feedback analysis. They want to improve the accuracy of sentiment extraction. Which TWO techniques should they apply? (Choose two.)

Which TWO techniques are most effective for improving factual accuracy in a generative AI model's responses? (Choose two.)

A healthcare startup has fine-tuned a Vertex AI PaLM 2 model on a dataset of medical records to generate patient summaries. The model produces fluent text but occasionally fabricates diagnoses not present in the input. The team has already tried increasing the training data size by 20% and adjusting the temperature from 0.7 to 0.2, but hallucinations persist. The summaries must be factually accurate for regulatory compliance. What should the team do next?

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

A customer support team uses a foundation model via the Gemini API to answer billing questions. Responses are often vague and sometimes omit required steps. The team wants to improve output quality without fine-tuning the model. Which approach should they use?

A healthcare provider uses a Gemini model on Vertex AI to summarize patient intake notes for clinicians. The summaries must consistently follow a fixed structure: chief complaint, history, medications, and plan. Early tests show the model sometimes reorders or omits sections. Which technique most reliably enforces the required structure?

A model generates biased output. Which technique is least effective?

A company is using a generative AI model to answer customer questions. The answers are often vague and do not use the company's specific terminology. They want to improve the relevance and specificity of the responses. Which technique should they use?

Which THREE techniques are commonly used to improve the overall quality and coherence of generative model outputs? (Choose three.)

A support team uses a generative AI assistant to answer customer questions. Agents report that the answers are often too long and include unnecessary background. The team wants the responses to be concise and directly address the question. Which prompt adjustment is most appropriate?

A data scientist is using the Gemini API to generate product descriptions for an e-commerce site. The descriptions are often too verbose and include speculative claims that are not in the product specifications. The scientist wants to reduce hallucinations and control the length of the output without retraining the model. What should they do?

A retail company is deploying a generative AI chatbot on Vertex AI to provide product recommendations. The chatbot uses a base foundation model with no fine-tuning. Users report that the chatbot sometimes gives offensive or insensitive responses. The team must quickly implement safety controls without modifying the model. They also want to reduce irrelevant off-topic answers. Which combination of techniques should they apply?

Refer to the exhibit. A team attempted to start a model tuning job but received the error 'Quota limit exceeded for tuning jobs in region us-central1'. What is the most appropriate action?

A team is using a generative AI model to answer customer questions about a complex product. They want to improve the factual accuracy and reduce hallucinations. Which TWO techniques should they apply? (Choose two.)

A marketing team uses a Gemini model through the Vertex AI API to draft campaign copy. The drafts are creative but frequently wander off topic and include unsupported claims. The team wants a low-effort improvement before considering any model customization. Which action should they take first?

A company is using a fine-tuned LLM for generating financial reports. They need to ensure that the output complies with regulatory standards and does not include speculative content. Which combination of techniques should they implement?

A marketing team is using an LLM on Vertex AI to generate product descriptions. They want to consistently control the creativity and randomness of the output. Which parameter should they adjust?

The exhibit shows the deployment configuration for a conversational AI model used in a finance application. Users report that responses are creative but often contain factually incorrect financial advice. Which parameter change would most improve factual accuracy?

After deploying a text-to-image model, the output images often contain distorted objects. The team suspects the prompt is too complex. Which prompt engineering technique should they try first?

A product team uses Gemini via the Vertex AI API to draft customer emails. The drafts are accurate but often too long and include unnecessary background. The team wants shorter, more direct outputs while keeping the same model. Which approach should they take?

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

A financial technology company has deployed a custom-tuned PaLM 2 model on Vertex AI to generate personalized investment recommendations for retail clients. The model was fine-tuned on a corpus of historical market data and advisory transcripts. Recently, the compliance team flagged that several recommendations contradicted SEC guidelines, and the model sometimes repeated prohibited statements from outdated training materials. The team has already implemented safety filters (e.g., blocking toxic content) and adjusted the model's system instructions to be more conservative. However, the issues persist. The model's deployment parameters are: temperature=0.4, top_p=0.9, max_output_tokens=500, and no grounding. The company must maintain compliance without significantly increasing latency. What should they do next?

A product team at a retailer is using Vertex AI Studio to build a Gemini-powered assistant that answers questions about their internal return policy. Early tests show the model invents policy details such as a 45-day return window, even though the official policy allows only 30 days. The team wants the assistant to answer strictly from a set of approved policy PDFs stored in a Cloud Storage bucket, and they want to avoid retraining the model. Which technique should they use?

A developer deployed a large language model on Vertex AI for real-time chat. Users report slow response times. The model generates sentences one word at a time. Which optimization should be applied to reduce latency?

A company wants to build a customer support chatbot that answers based on internal documentation. They use Vertex AI Search and want to ensure the model only uses retrieved documents. What should they do?

A healthcare company is using a generative AI model to draft patient education materials. The model sometimes generates content that includes specific medical advice, which could be harmful if inaccurate. The company wants to ensure that the model's outputs are safe and do not provide medical recommendations. Which technique should they implement?

Which TWO techniques are effective for reducing bias in generative AI model outputs?

A financial analyst uses generative AI to summarize earnings reports. The summaries vary in style. Which THREE methods can improve consistency? (Choose three.)

A user reports that the model's response to the same prompt varies significantly across different calls. Which parameter change would most likely reduce variability?

After fine-tuning a model on customer support data, the model starts using profanity. What is the most effective mitigation?

A marketing team uses a Gemini model to generate ad copy. They notice the outputs are repetitive and lack variety across multiple runs for the same prompt. They want more diverse creative options without sacrificing relevance. Which parameter adjustment should they make?

A research lab is fine-tuning a large language model on a small dataset of medical records. They observe that the model overfits, memorizing specific patient details and producing outputs that violate privacy regulations. Which technique should they apply to improve generalization and reduce memorization?

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

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

A global software company uses a generative AI model to produce localized release notes. Outputs are accurate but inconsistently formatted: some use tables, some bullet lists, and some paragraphs, which breaks the publishing pipeline. The team wants stable, machine-parseable formatting across all runs. Which technique should they prioritize?

A retail company uses a generative AI model to create personalized product recommendations. The model sometimes generates recommendations that include products the company does not sell. Which technique should be used to prevent the model from generating non-existent products?

A streaming platform uses a large generative model for personalized content suggestions. Budget constraints require minimizing inference costs without significantly degrading quality. Which approach is most effective?

A developer is using the Gemini API to generate code snippets. They notice the outputs often contain deprecated API calls. Which parameter adjustment or prompt strategy would most effectively encourage the model to use current APIs?

A logistics company built a Gemini-powered assistant that answers driver questions about routes and hours-of-service rules. The assistant performs well on common questions but produces fabricated regulatory citations when asked about rare edge cases. The team has a curated set of correct answers for these edge cases and wants the model to adopt that behavior reliably. Which approach best fits?

A financial analyst is using a large language model to generate executive summaries from lengthy earnings call transcripts. The summaries often miss key financial figures and include irrelevant details. Which technique should be used to improve the relevance and accuracy of the summaries?

An AI team is building a customer support chatbot for a telecom company using a fine-tuned LLM on Vertex AI. The model performs well on common issues but fails to answer correctly for rare or novel problems, often providing plausible-sounding but incorrect solutions. The team has a large corpus of internal troubleshooting documents. They want to minimize incorrect answers while keeping latency low. Which approach should they take?

A company is prompt engineering a model for customer support. They want to reduce hallucination (false information) in responses. Which TWO techniques are most effective? (Choose two.)

A development team is integrating a large language model into a healthcare application. They need to reduce the risk of generating harmful medical advice. Which THREE measures should they implement? (Choose three.)

A healthcare organization needs a generative AI model to answer medical questions using proprietary clinical guidelines. They have a large dataset of doctor-patient interactions. Should they fine-tune a pre-trained model or use Retrieval-Augmented Generation (RAG)?

A healthcare organization is using a generative AI model to summarize patient discharge instructions. They need to ensure the summaries are accurate and do not omit critical information. Which technique should they implement to reduce the risk of omissions?

A healthcare startup fine-tunes a model to generate patient education materials. They want to ensure the model never gives medical advice, only information. They add a safety instruction, but the model sometimes still gives advice. What advanced technique should they apply?

Which technique allows a model to incorporate real-time data from external APIs?

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?

A developer is building a customer support chatbot using a large language model. The chatbot frequently generates plausible-sounding but incorrect answers to product questions. Which technique should be applied to improve factual accuracy?

A team monitors their generative AI model on Vertex AI. They notice output quality declining. Which metric is most likely the root cause?

A content generation model for e-commerce product descriptions repeats the same phrases across multiple descriptions (e.g., 'high-quality', 'best-in-class'). The team wants more varied and engaging output. Which parameter adjustment is most appropriate?

A product team at a retail company is using a foundation model on Vertex AI to generate short marketing taglines for new products. They find the outputs are often too long and sometimes include extra commentary. They want to constrain the model to produce only a single concise tagline. Which parameter should they adjust?

A software development team builds an internal code assistant using a generative model. The assistant writes Python functions that often contain security vulnerabilities such as SQL injection or command injection. The team wants to mitigate these vulnerabilities without adding a manual review step for every code snippet, as that would slow development. They have access to a static analysis security scanner API. Which approach best addresses the vulnerabilities while maintaining developer velocity?

A developer uses a generative AI model with the system instruction shown. The response is correct but very brief. Which parameter adjustment could encourage more detail without losing accuracy?

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?

A logistics company uses a generative AI model to draft incident reports from sensor logs. Reviewers find the reports are often incomplete, missing fields such as root cause and corrective action. The team wants to improve output completeness without retraining the model. Which TWO techniques should they use? (Choose two.)

A financial services firm uses a Gemini model to generate quarterly risk summaries from internal reports. Reviewers note that summaries sometimes contradict the source tables. The team wants the model to reason step by step over the figures before writing the summary. Which technique should they use?

Which THREE are best practices for designing prompts for a generative AI model?

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

A software company is using a large language model to generate code snippets from natural language descriptions. The generated code often has syntax errors and does not follow the company's coding standards. Which approach is most effective to improve the quality of the generated code?

A data scientist is using a large language model to generate product descriptions. The descriptions are often too verbose. Which parameter adjustment is most appropriate?

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

A financial services firm is using a large language model to generate quarterly investment summaries from raw market data. The summaries occasionally contain fabricated statistics and sometimes omit key risk factors. The team wants to improve factual accuracy and completeness without retraining the model. Which TWO techniques should they apply? (Choose two.)

A marketing team is using a generative AI model on Vertex AI to create ad copy for a new product launch. The initial outputs are generic and do not reflect the brand's tone. The team wants to quickly improve the outputs without retraining the model. They have a set of example ad copies that exemplify the desired tone. Which technique should they use?

A financial services firm uses a generative AI model to draft client emails. The drafts are accurate but sometimes use an overly casual tone. The firm wants to enforce a consistently formal tone across all drafts. Which approach is most reliable for this requirement?

A company uses Vertex AI PaLM for code generation. The code often contains security vulnerabilities. Which improvement should be applied?

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?

A company uses a text generation model for customer support but notices it occasionally provides outdated information. Which technique should they implement to improve output accuracy?

A team uses Vertex AI Generative AI Studio to tune a model via RLHF. After tuning, the model outputs are bland. What likely went wrong?

A chatbot built with Vertex AI PaLM API often provides outdated information about company policies because the training data is months old. Which approach should the team use?

A company is using a generative AI model to create personalized email responses to customer inquiries. The responses sometimes contain factual errors or irrelevant information. The company wants to improve the accuracy and relevance of the responses. Which TWO techniques should they use? (Choose two.)

What is the primary purpose of a system instruction in the Gemini API?

A global bank uses a Gemini model on Vertex AI to generate personalized investment summaries for clients in multiple regions. Compliance requires that the model never recommend products prohibited in a given region. The team wants a control that enforces these rules regardless of how the prompt is phrased. Which approach should they use?

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?

Which THREE strategies should be combined to effectively reduce biased outputs in a generative AI model? (Choose three.)

A company is using a large language model for automated translation of legal contracts. They find that the translations sometimes alter the meaning of specific clauses. Which TWO approaches would most effectively preserve the original meaning? (Choose two.)

A marketing team uses Gemini in Vertex AI to generate campaign taglines. The first drafts are generic and closely mirror the prompt wording. They want more distinctive, varied taglines from the same model without changing the model itself. Which parameter should they adjust?

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

A media company uses a Gemini model to produce short news digests from long articles. Editors complain that digests vary in length and sometimes bury the key fact in the middle. The team wants a repeatable, machine-checkable structure for every digest. Which technique should they use?

A data scientist fine-tunes a generative image captioning model to describe medical images. The model outputs safe but very generic captions (e.g., 'An image of cells'). The goal is to produce more specific, clinically relevant descriptions. Which approach is most effective?

A healthcare analytics team uses a Gemini model to generate patient-friendly discharge summaries from clinical notes. Clinicians report that summaries occasionally omit critical follow-up instructions. The team must improve recall of these instructions without retraining the model. Which two techniques should they apply? (Choose two.)

A developer wants to improve the factual accuracy of the model's summaries. Based on the exhibit, what should they do?

A financial services firm is using a foundation model on Vertex AI to generate investment summaries from quarterly reports. The summaries are accurate but often miss key financial metrics and trends. The team cannot afford to fine-tune the model frequently. Which technique should they use to improve the completeness and relevance of the summaries without modifying the model?

A healthcare chatbot must avoid hallucinations. Which TWO techniques should the team implement? (Choose two.)

A legal firm uses a generative AI to draft contracts. They want the output to follow a specific clause structure. Which technique should they use in the prompt?

A marketing agency uses a generative AI model to create slogans for ad campaigns. The model outputs generic slogans like 'Quality you can trust' that lack originality. The agency has a library of past award-winning slogans and wants to generate more creative and brand-specific outputs. They have a requirement that the model must not produce slogans longer than 15 words. Which technique should they prioritize?

A product team uses a translation model to convert English product descriptions into French. The model mixes formal and informal French dialects. Which simple prompt modification likely solves this?

A team is deploying a text generation model for legal document review. They observe that the model occasionally generates factually incorrect legal citations. Which approach best reduces this issue?

A team is using a generative AI model to create summaries of customer feedback. The summaries are often too long and include unnecessary details. The team wants to make the summaries more concise without losing key information. Which technique should they use?

A developer is using Vertex AI PaLM 2 to generate product descriptions. The output is often too verbose and includes irrelevant details. Which technique should the developer apply?

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?

A company is using Vertex AI to generate customer support summaries from chat logs. They notice that the summaries sometimes include irrelevant details from the conversation. Which technique should they use to reduce irrelevant details?

A developer is using the Gemini API to build a chatbot. They want the model to always respond in a friendly, professional tone. Which prompt engineering technique should they use?

A marketing team uses a text generation model to draft campaign copy. They want the output to consistently follow a specific brand voice and include a call to action at the end of every draft. Which technique should they apply?