NCA-GENL 無料問題集「NVIDIA Generative AI LLMs」

（A）RAG is a methodology that combines an information retrieval component with a response generator.

（B）RAG is an architecture used to optimize the output of an LLM by retraining the model with domain- specific data.

（C）RAG is a technique used to fine-tune pre-trained LLMs for improved performance.

（D）RAG is a method for manipulating and generating text-based data using Transformer-based LLMs.

（A）To focus on relevant parts of the input sequence for use in the downstream task.

（B）To compress the input sequence for faster processing.

（C）To generate random noise for improved model robustness.

（D）To convert text into numerical representations.

（A）Leveraging the system message.

（B）Choosing another model architecture.

（C）Increasing the model's parameter count.

（D）Training the model with additional data.

（A）To act as a replacement for traditional programming languages.

（B）To orchestrate LLM components into complex workflows.

（C）To reduce the size of AI foundation models.

（D）To directly manage the hardware resources used by LLMs.

（A）Single hold-out validation with a fixed test set.

（B）Grid search for hyperparameter tuning.

（C）Bootstrapping with random sampling.

（D）Stratified k-fold cross-validation.