Bài kiểm tra có liên kết hướng dẫn · Trung bình Cấp độ
Câu đố LLMOps và MLOps
So sánh các mối quan tâm vận hành dành riêng cho LLM với các thực tiễn MLOps được chia sẻ qua các lời nhắc, truy xuất, đánh giá, chi phí và giám sát.
Câu hỏi 1 của 8
Which change can alter an LLM application's behavior without retraining foundation-model weights?
Xem trước mọi câu hỏi8 câu hỏi
Câu trả lời và giải thích xuất hiện khi bạn làm bài kiểm tra.
- Which change can alter an LLM application's behavior without retraining foundation-model weights?
- A prompt template or retrieval index update
- A dashboard color change only
- A cloud region name in documentation
- A model card font size
- Why version a retrieval corpus or index separately from the generator?
- It makes the index part of model weights
- It lets teams isolate whether changed evidence retrieval caused an output regression
- It eliminates document access controls
- It guarantees factual answers
- Which metric is specific to common LLM API cost tracking?
- GPU occupancy only
- Gini impurity
- Input and output token usage
- Number of class labels
- Why run evaluation cases after changing a prompt?
- Evaluation is only for GPU kernels
- Prompts cannot affect model responses
- A prompt change retrains the model automatically
- Prompt wording can alter outputs, tool use and refusal behavior
- What can model-based judging fail to detect?
- Prompt version changes
- Factual errors or evaluator bias shared with the candidate
- Token counts
- Retrieval index updates
- Which shared MLOps practice remains useful for LLM applications?
- Using only training accuracy
- Ignoring data governance
- Staged release, monitoring and rollback
- Always retraining full weights per request
- Why can a hosted model alias limit reproducibility?
- Hosted models never return metadata
- Aliases contain the full model weights
- The prompt cannot be stored
- Provider behavior may change behind an identifier
- Which security issue can arise from retrieved external documents?
- Untrusted content can include prompt-injection instructions
- Documents automatically retrain the model
- Retrieval guarantees valid access permissions
- Embeddings remove sensitive data