引导式测验 · 中等 等级

上下文窗口测验

检查令牌上下文预算、输入和输出分配、长输入评估限制、检索权衡以及请求超出容量时的行为。

相关引导路径上下文窗口
问题 1 的 8

模型的上下文窗口衡量什么？

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. 模型的上下文窗口衡量什么？
    • 聊天界面的屏幕分辨率
    • 模型可以一次考虑的最大文本量（以标记为单位）
    • 多少用户可以同时聊天
    • 模型的总训练数据集大小
  2. How should a token be interpreted when budgeting language-model context?
    • As exactly one full word in every language
    • As exactly one sentence in every tokenizer
    • As a tokenizer-defined unit whose relation to words depends on the model and text
    • As the API password used to send a request
  3. In a decoder-style request with a shared input-and-continuation budget, which supplied material uses that budget?
    • Instructions, conversation turns, document tokens, and the generated continuation
    • Only the latest user message
    • Only stored application files that were never supplied
    • Only generated output, with input always free
  4. Under a dense full-attention pairwise-interaction model, how does comparison count scale when a request's token length doubles?
    • It becomes only twice as large under that model
    • It stays unchanged regardless of length
    • It becomes half as large
    • It becomes four times as large under the quadratic model
  5. “迷失在中间”问题是指模型倾向于：
    • 当输入很长时崩溃
    • 将文档的中间部分翻译成另一种语言
    • 长输入的开头和结尾的信息比中间的信息更好回忆
    • 完全忽略第一句和最后一句
  6. Why can retrieval be combined with a language model's limited context window?
    • It guarantees the lowest total cost for every workflow
    • It selects passages to supply rather than requiring the whole knowledge base as input
    • It permanently increases the model's supported token capacity
    • It removes the need to evaluate generated answers
  7. In an illustrative shared context budget of 8,000 tokens, input uses 6,500. How many tokens remain before other limits or overhead?
    • 6,500
    • 8,000
    • 14,500
    • 1,500
  8. What can happen when an input exceeds a language model interface's supported context?
    • Rejection, truncation, or application-side shortening, depending on the setup
    • Automatic permanent memory of all excluded text
    • Guaranteed silent deletion of the oldest message in every system
    • Automatic expansion of every model's trained architecture