가이드 연계 퀴즈 · 중간 레벨

엔트로피 기반 샘플링 퀴즈

다음 토큰 엔트로피와 진실 신뢰도를 구별하고, 엔트로피와 바렌트로피를 설명하고, 적응형 디코딩 휴리스틱의 한계를 확인합니다.

관련 가이드 경로엔트로피 기반 샘플링
질문 1 의 8

What does next-token entropy measure in an entropy-aware decoder?

모든 질문 미리보기8 질문

퀴즈를 풀면 정답과 설명이 나타납니다.

  1. What does next-token entropy measure in an entropy-aware decoder?
    • How spread out probability is across the model’s possible next tokens
    • Whether the model’s factual claim is true
    • 모델의 매개변수 수
    • The total number of tokens already generated
  2. A low-entropy next-token distribution most directly indicates that:
    • The predicted answer is guaranteed factual
    • Probability is concentrated on a small set of tokens
    • The model has no uncertainty about the entire conversation
    • Every token in the vocabulary is equally likely
  3. 다음 토큰 분포의 Shannon 엔트로피는 다음과 같이 계산됩니다.
    • 로짓의 합
    • 최대 확률에서 최소 확률을 뺀 값
    • -토큰에 대한 p_i 로그 p_i 합계
    • 어휘의 토큰 수
  4. What does varentropy measure in some entropy-aware decoding schemes?
    • The variance of model parameter counts
    • The factual accuracy of the next sentence
    • 훈련 시대의 수
    • Variation in token-level surprisal values under the distribution
  5. When an entropy-aware system sees a high-entropy next-token distribution, what can it reasonably conclude?
    • The distribution is more spread out and may merit a task-specific decoding policy
    • The model is certainly hallucinating
    • The highest-probability token is false
    • The output must be stopped immediately
  6. What is a practical limit of using entropy to guide generation?
    • Entropy cannot be computed from probabilities
    • A chosen entropy policy does not by itself guarantee fewer factual errors
    • Entropy removes the need for model weights
    • Entropy forces all tokens to have equal probability
  7. A low-entropy model answer agrees with a user’s false claim. What does the entropy value establish?
    • That the claim has been independently verified
    • That every other candidate is impossible
    • Only that the model’s next-token distribution is concentrated, not that the claim is true
    • That the answer came from a reliable source
  8. How should a team choose thresholds for an entropy-triggered retrieval policy?
    • Assume one threshold works for all models and contexts
    • Choose the threshold from the model name
    • Treat every high-entropy token as a proven error
    • Evaluate the policy on representative tasks and measure whether retrieval improves outcomes