Oracle 1Z0-1127-25 問題集

質問 1：
What is the function of the Generator in a text generation system?
A. To collect user queries and convert them into database search terms
B. To store the generated responses for future use
C. To generate human-like text using the information retrieved and ranked, along with the user's original query
D. To rank the information based on its relevance to the user's query
正解：C
解説: (Topexam メンバーにのみ表示されます)

質問 2：
What happens if a period (.) is used as a stop sequence in text generation?
A. The model stops generating text after it reaches the end of the first sentence, even if the token limit is much higher.
B. The model stops generating text after it reaches the end of the current paragraph.
C. The model generates additional sentences to complete the paragraph.
D. The model ignores periods and continues generating text until it reaches the token limit.
正解：A
解説: (Topexam メンバーにのみ表示されます)

質問 3：
Which statement best describes the role of encoder and decoder models in natural language processing?
A. Encoder models convert a sequence of words into a vector representation, and decoder models take this vector representation to generate a sequence of words.
B. Encoder models take a sequence of words and predict the next word in the sequence, whereas decoder models convert a sequence of words into a numerical representation.
C. Encoder models are used only for numerical calculations, whereas decoder models are used to interpret the calculated numerical values back into text.
D. Encoder models and decoder models both convert sequences of words into vector representations without generating new text.
正解：A
解説: (Topexam メンバーにのみ表示されます)

質問 4：
What is the purpose of Retrieval Augmented Generation (RAG) in text generation?
A. To retrieve text from an external source and present it without any modifications
B. To store text in an external database without using it for generation
C. To generate text based only on the model's internal knowledge without external data
D. To generate text using extra information obtained from an external data source
正解：D
解説: (Topexam メンバーにのみ表示されます)

質問 5：
What is the main advantage of using few-shot model prompting to customize a Large Language Model (LLM)?
A. It significantly reduces the latency for each model request.
B. It allows the LLM to access a larger dataset.
C. It provides examples in the prompt to guide the LLM to better performance with no training cost.
D. It eliminates the need for any training or computational resources.
正解：C
解説: (Topexam メンバーにのみ表示されます)

質問 6：
What does "k-shot prompting" refer to when using Large Language Models for task-specific applications?
A. Explicitly providing k examples of the intended task in the prompt to guide the model's output
B. Providing the exact k words in the prompt to guide the model's response
C. Limiting the model to only k possible outcomes or answers for a given task
D. The process of training the model on k different tasks simultaneously to improve its versatility
正解：A
解説: (Topexam メンバーにのみ表示されます)

質問 7：
How can the concept of "Groundedness" differ from "Answer Relevance" in the context of Retrieval Augmented Generation (RAG)?
A. Groundedness measures relevance to the user query, whereas Answer Relevance evaluates data integrity.
B. Groundedness pertains to factual correctness, whereas Answer Relevance concerns query relevance.
C. Groundedness refers to contextual alignment, whereas Answer Relevance deals with syntactic accuracy.
D. Groundedness focuses on data integrity, whereas Answer Relevance emphasizes lexical diversity.
正解：B
解説: (Topexam メンバーにのみ表示されます)

質問 8：
What is the purpose of frequency penalties in language model outputs?
A. To randomly penalize some tokens to increase the diversity of the text
B. To ensure that tokens that appear frequently are used more often
C. To reward the tokens that have never appeared in the text
D. To penalize tokens that have already appeared, based on the number of times they have been used
正解：D
解説: (Topexam メンバーにのみ表示されます)

質問 9：
What does "Loss" measure in the evaluation of OCI Generative AI fine-tuned models?
A. The percentage of incorrect predictions made by the model compared with the total number of predictions in the evaluation
B. The level of incorrectness in the model's predictions, with lower values indicating better performance
C. The difference between the accuracy of the model at the beginning of training and the accuracy of the deployed model
D. The improvement in accuracy achieved by the model during training on the user-uploaded dataset
正解：B
解説: (Topexam メンバーにのみ表示されます)