GENAI-ASSOCIATE practice questions 61–70

1. Question 61 · 92 in bank

   When developing an LLM application, it’s crucial to ensure that the data used for training the model complies with licensing requirements to avoid legal risks. Which action is most appropriate to avoid legal risks?

   • AOnly use data explicitly labeled with an open license and ensure the license terms are followed.
   • BAny LLM outputs are reasonable to use because they do not reveal the original sources of data directly.
   • CReach out to the data curators directly to gain written consent for using their data.
   • DUse any publicly available data as public data does not have legal restrictions.

   Show answer

   Answer: A

   Next question

2. Question 62 · 92 in bank

   A Generative AI Engineer at a home appliance company has been asked to design an LLM based application that accomplishes the following business objective: answer customer questions on home appliances using the associated instruction manuals. Which set of high-level tasks should the Generative AI Engineer’s system perform?

   • ASplit instruction manuals into chunks and embed into a vector store. Use the question to retrieve best matched chunks of manual, and use the LLM to generate a response to the user based upon the manual retrieved.
   • BCreate an interaction matrix of historical user questions and appliance instruction manuals. Use ALS to factorize the matrix and create embeddings. Calculate the embeddings of new queries and use them to find the best manual. Use an LLM to generate a response to the question based upon the manual retrieved.
   • CCalculate averaged embeddings for each instruction manual, compare embeddings to user query to find the best manual. Pass the best manual with user query into an LLM with a large context window to generate a response to the employee.
   • DUse an LLM to summarize all of the instruction manuals. Provide summaries of each manual and user query into an LLM with a large context window to generate a response to the user.

   Show answer

   Answer: A

   Next question

3. Question 63 · 92 in bank

   A Generative AI Engineer is deciding between using LSH (Locality Sensitive Hashing) and HNSW (Hierarchical Navigable Small World) for indexing their vector database. Their top priority is semantic accuracy. Which approach should the Generative AI Engineer use to evaluate these two techniques?

   • ACompare the cosine similarities of the embeddings of returned results against those of a representative sample of test inputs
   • BCompare the Bilingual Evaluation Understudy (BLEU) scores of returned results for a representative sample of test inputs
   • CCompare the Recall-Oriented-Understudy for Gisting Evaluation (ROUGE) scores of returned results for a representative sample of test inputs
   • DCompare the Levenshtein distances of returned results against a representative sample of test inputs

   Show answer

   Answer: A

   Next question

4. Question 64 · 92 in bank

   A Generative AI Engineer is developing an LLM application that users can use to generate personalized birthday poems based on their names. Which technique would be most effective in safeguarding the application, given the potential for malicious user inputs?

   • AImplement a safety filter that detects any harmful inputs and ask the LLM to respond that it is unable to assist
   • BReduce the time that the users can interact with the LLM
   • CAsk the LLM to remind the user that the input is malicious but continue the conversation with the user
   • DIncrease the amount of compute that powers the LLM to process input faster

   Show answer

   Answer: A

   Next question

5. Question 65 · 92 in bank

   What is an effective method to preprocess prompts using custom code before sending them to an LLM?

   • ADirectly modify the LLM’s internal architecture to include preprocessing steps
   • BIt is better not to introduce custom code to preprocess prompts as the LLM has not been trained with examples of the preprocessed prompts
   • CRather than preprocessing prompts, it’s more effective to postprocess the LLM outputs to align the outputs to desired outcomes
   • DWrite a MLflow PyFunc model that has a separate function to process the prompts

   Show answer

   Answer: D

   Next question

6. Question 66 · 92 in bank

   A Generative Al Engineer is tasked with developing a RAG application that will help a small internal group of experts at their company answer specific questions, augmented by an internal knowledge base. They want the best possible quality in the answers, and neither latency nor throughput is a huge concern given that the user group is small and they’re willing to wait for the best answer. The topics are sensitive in nature and the data is highly confidential and so, due to regulatory requirements, none of the information is allowed to be transmitted to third parties. Which model meets all the Generative Al Engineer’s needs in this situation?

   • ADolly 1.5B
   • BOpenAI GPT-4
   • CBGE-large
   • DLlama2-70B

   Show answer

   Answer: D

   Next question

7. Question 67 · 92 in bank

   A Generative AI Engineer is testing a simple prompt template in LangChain using the code below, but is getting an error.

   

   Assuming the API key was properly defined, what change does the Generative AI Engineer need to make to fix their chain?

   • A//IMG//
   • B//IMG//
   • C//IMG//
   • D//IMG//

   Show answer

   Answer: D

   Next question

8. Question 68 · 92 in bank

   A Generative AI Engineer has a provisioned throughput model serving endpoint as part of a RAG application and would like to monitor the serving endpoint’s incoming requests and outgoing responses. The current approach is to include a micro-service in between the endpoint and the user interface to write logs to a remote server. Which Databricks feature should they use instead which will perform the same task?

   • AVector Search
   • BLakeview
   • CDBSQL
   • DInference Tables

   Show answer

   Answer: D

   Next question

9. Question 69 · 92 in bank

   A Generative AI Engineer is building a production-ready LLM system which replies directly to customers. The solution makes use of the Foundation Model API via provisioned throughput. They are concerned that the LLM could potentially respond in a toxic or otherwise unsafe way. They also wish to perform this with the least amount of effort. Which approach will do this?

   • AAsk users to report unsafe responses
   • BHost Llama Guard on Foundation Model API and use it to detect unsafe responses.
   • CAdd some LLM calls to their chain to detect unsafe content before returning text
   • DAdd a regex expression on inputs and outputs to detect unsafe responses.

   Show answer

   Answer: B

   Next question

10. Question 70 · 92 in bank

    A Generative AI Engineer received the following business requirements for an internal chatbot. The internal chatbot needs to know what types of questions the user asks and route them to appropriate models to answer the questions. For example, the user might ask about historical failure rates of a specific electrical part. Another user might ask about how to troubleshoot a piece of electrical equipment. Available data sources include a database of electrical equipment PDF manuals and also a table with information on when an electrical part experiences failure. Which workflow supports such a chatbot?

    • AParse the electrical equipment PDF manuals into a table of question and response pairs. That way, the same chatbot can query tables easily to answer questions about both historical failure rates and equipment troubleshooting.
    • BThe chatbot should be implemented as a multi-step LLM workflow. First, identify the type of question asked, then route the question to the appropriate model. If it’s a historical failure rate question, send the query to a text-to-SQL model. If it’s a troubleshooting question, then send the query to another model that summarizes the equipment-specific document and generates the response.
    • CThere should be two different chatbots handling different types of user queries.
    • DThe table with electrical part failures should be converted into a text document first. That way, the same chatbot can use the same document retrieval process to generate answers regardless of question types.

    Show answer

    Answer: B

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

GENAI-ASSOCIATE practice, question 61. 92 questions available.