C_AIG_2412問題集、SAP実際の試験問題

質問 1

Which technique is used to supply domain-specific knowledge to an LLM?

A. Fine-tuning the model on general data

B. Prompt template expansion

C. Retrieval-Augmented Generation

D. Domain-adaptation training

正解: C

解説: (PassTest メンバーにのみ表示されます)

質問 2

Which of the following are grounding principles included in SAP's AI Ethics framework? Note: There are 3 correct answers to this question.

A. Avoid bias and discrimination

B. Human agency and oversight

C. Transparency and explainability

D. Store all user data for legal proceedings

E. Maximize business profits

正解: A,B,C

解説: (PassTest メンバーにのみ表示されます)

質問 3

How can few-shot learning enhance LLM performance?

A. By enhancing the model's computational efficiency

B. By offering input-output pairs that exemplify the desired behavior

C. By providing a large training set to improve generalization

D. By reducing overfitting through regularization techniques

正解: B

解説: (PassTest メンバーにのみ表示されます)

質問 4

What are some components of the training pipeline in SAP AI Core? Note: There are 2 correct answers to this question.

A. Executables that define the training process

B. Input datasets stored in a hyperscaler object store

C. The SAP HANA database for model storage

D. Automated deployment to Kubernetes clusters

正解: A,B

解説: (PassTest メンバーにのみ表示されます)

質問 5

What does the Prompt Management feature of the SAP AI launchpad allow users to do?

A. Provide personalized user interactions

B. Create and edit prompts

C. Interact with models through a conversational interface

D. Access and manage saved prompts and their versions

正解: B,D

解説: (PassTest メンバーにのみ表示されます)

質問 6

What must be defined in an executable to train a machine learning model using SAP AI Core? Note: There are 2 correct answers to this question.

A. User scripts to manually execute pipeline steps

B. Infrastructure resources such as CPUs or GPUs

C. Pipeline containers to be used

D. Deployment templates for SAP AI Launchpad

正解: B,C

解説: (PassTest メンバーにのみ表示されます)

質問 7

You want to assign urgency and sentiment categories to a large number of customer emails. You want to get a valid json string output for creating custom applications. You decide to develop a prompt for the same using generative Al hub.
What is the main purpose of the following code in this context?
prompt_test = """Your task is to extract and categorize messages. Here are some examples:
{{?technique_examples}}
Use the examples when extract and categorize the following message:
{{?input}}
Extract and return a json with the following keys and values:
-"urgency" as one of {{?urgency}}
-"sentiment" as one of {{?sentiment}}
"categories" list of the best matching support category tags from: {{?categories}} Your complete message should be a valid json string that can be read directly and only contains the keys mentioned in t import random random.seed(42) k = 3 examples random. sample (dev_set, k) example_template = """<example> {example_input} examples
'\n---\n'.join([example_template.format(example_input=example ["message"], example_output=json.dumps (example[ f_test = partial (send_request, prompt=prompt_test, technique_examples examples, **option_lists) response = f_test(input=mail["message"])

A. Generate random examples for language model training

B. Train a language model from scratch

C. Preprocess a dataset for machine learning

D. Evaluate the performance of a language model using few-shot learning

正解: D

解説: (PassTest メンバーにのみ表示されます)

SAP Certified Associate - SAP Generative AI Developer - C_AIG_2412 模擬練習