引导式测验 · 中等 等级

N 次最佳抽样和重新排名测验

了解 N 中最佳选择、评分器限制、推理时间成本以及对更多候选者进行采样背后的概率假设。

相关引导路径N 次最佳采样和重新排序
问题 1 的 8

best-of-N采样的核心思想是什么？

预览每个问题8 问题

当您参加测验时，就会出现答案和解释。

  1. best-of-N采样的核心思想是什么？
    • 生成 N 个候选输出并用评分器选择最好的一个
    • 训练模型 N 次并平均权重
    • 仅使用模型产生的第一个输出
    • 将词汇量减少到 N 个标记
  2. When is best-of-N most likely to help?
    • When every output is equally good
    • When the model sometimes samples a correct candidate and a reliable verifier can identify it
    • When the task has no way to assess candidates
    • When sampling is disabled
  3. 是什么在很大程度上决定了“N 中最佳”是否能够真正改善结果？
    • 用户界面的颜色
    • 仅提示的长度
    • 评分者或验证者的质量和稳健性
    • 模型的词汇量大小
  4. What can happen when N becomes large and the reward model is an imperfect proxy?
    • The model’s tokenizer is removed
    • The model forgets its training weights
    • All candidates become identical
    • Selection can favor outputs that exploit scorer errors and reduce true quality
  5. 哪种简单的重新排名策略也称为自我一致性？
    • 对抽样答案进行多数投票
    • 选择最长的答案
    • 选择随机样本
    • 总是取概率最低的输出
  6. What mainly drives the generation cost of best-of-N?
    • Only the number of vocabulary entries
    • The total amount of text generated across the sampled candidates
    • The user interface color
    • The number of model training runs
  7. If each independent sample succeeds with probability p and a perfect verifier picks any success, what is the chance at least one of N samples succeeds?
    • p/N
    • N−p
    • 1−(1−p)^N
    • 1−p^N
  8. Which assumption is needed for the simple 1−(1−p)^N success formula?
    • Every response has a different length
    • The model is retrained after each sample
    • The reward model has no parameters
    • The candidate samples are independent and the verifier recognizes success perfectly