引導式測驗 · 中等 等級

為什麼人工智慧拒絕無害請求測驗

識別錯誤拒絕、澄清合法背景並保留安全邊界,而不試圖繞過對有害請求的保護。

問題 1 的 8

您會如何定義過度拒絕?

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. 您會如何定義過度拒絕?
    • Answering a harmful request fully
    • Declining a benign request because it is incorrectly treated as unsafe
    • Asking a clarifying question
    • Refusing a request that would enable serious harm
  2. What was the scope of OR-Bench’s 2024 evaluation?
    • Every user conversation across all current chatbots
    • Only 25 harmless prompts
    • A test of image-generation quality
    • 80,000 seemingly toxic benign prompts, a hard subset, toxic controls, and 25 models across eight families
  3. 為什麼不應將 OR-Bench 的拒絕率視為普遍標準?
    • It depends on benchmark categories, model versions, and how prompts were labeled
    • The benchmark contains no prompts
    • All models have identical safety behavior
    • Refusals cannot be counted
  4. 當合理的請求被誤解時,什麼可能有幫助?
    • Claiming the model must ignore all safeguards
    • Hiding the real purpose
    • Clarifying the benign goal, context, and safe boundaries
    • Adding instructions to bypass policy
  5. 過度拒絕緩解的目標是回答每一個請求嗎?
    • Yes, all refusals are errors
    • No; the system should reduce false refusals while still refusing harmful assistance
    • Yes, if a user says it is safe
    • No, because all benign requests should be refused
  6. Why test benign and harmful prompts that share vocabulary?
    • It checks whether the model uses context rather than only surface words
    • It guarantees zero false refusals
    • It tests response formatting only
    • It removes the need for safety tests
  7. 產品團隊除了錯誤拒絕外,還應該衡量什麼?
    • Only average answer length
    • Only positive user ratings
    • The number of words in the policy
    • Unsafe compliance on genuinely harmful requests
  8. If a request remains unsafe after clarification, how should a user proceed?
    • Use a jailbreak to force an answer
    • Repeat the request with coded wording
    • Accept the boundary and ask for a safe alternative
    • Assume every refusal is mistaken