引導式測驗 · 中等 等級

LLM評估框架:Promptfoo與DeepEval測驗

比較 Promptfoo 和 DeepEval 工作流程、測試案例、確定性斷言、判斷指標、CI 使用以及每個仍需要的人工審核。

問題 1 的 8

What core problem do both Promptfoo and DeepEval address?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. What core problem do both Promptfoo and DeepEval address?
    • Making LLM behavior testable through structured cases, repeatable runs, and suitable automated checks
    • Training new base models from scratch
    • Compressing model weights for faster inference
    • 將提示翻譯成多種語言
  2. How is a Promptfoo evaluation typically configured?
    • Through a compiled binary with no config file
    • Through a YAML file listing prompts, providers, test cases and assertions
    • Through a spreadsheet macro
    • Through direct edits to the model's weights
  3. What does DeepEval's faithfulness metric primarily check?
    • Whether the output uses correct grammar
    • Whether the response is shorter than 100 words
    • Whether a RAG answer stays grounded in the retrieved context rather than adding unsupported claims
    • Whether the model responded within 1 second
  4. In the support-chatbot example, what caused the test suite to catch a regression?
    • The model started responding in a different language
    • The API key expired mid-test
    • The test suite was run twice by accident
    • A prompt edit accidentally dropped a required refund-policy disclaimer
  5. How does DeepEval structure an individual test case?
    • As an LLMTestCase object holding input, actual output, and optionally retrieval context and expected output
    • As a single string with no metadata
    • As a raw HTTP request log
    • As an image file
  6. What remains necessary when an evaluation framework reports passing metric scores?
    • Assume the application is safe in every context
    • Human review and task-specific validation for ambiguous or high-risk behavior
    • Retire the test dataset immediately
    • Trust the metric threshold as universal proof
  7. Why might a CI pipeline fail a build using one of these frameworks?
    • Because the repository has too many files
    • Because the model's API key is stored in an environment variable
    • Because a numeric metric score, such as faithfulness, falls below a configured threshold
    • Because the test suite runs on a weekend
  8. Why do many model-graded assertions and metrics require an extra API call per test case?
    • Because every test case must be translated first
    • Because the test framework requires two models to run simultaneously for redundancy
    • Because outputs must be compressed before scoring
    • Because they use a separate judge-model call to score the output against a rubric