引導式測驗 · 硬 等級

函數向量和任務表示測驗

研究如何從注意力頭中提取函數向量,注入隱藏狀態,並跨任務情境進行測試。

相關引導路徑函數向量和任務表示
問題 1 的 8

What does a function vector represent in the studied language models?

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 does a function vector represent in the studied language models?
    • A compact activation-space representation associated with a demonstrated task
    • The model’s full weight matrix
    • A single token embedding in every setting
    • The optimizer’s learning rate
  2. 函數向量通常是如何建構的?
    • 透過詞彙表中的所有字詞嵌入求和
    • 透過對範例提示上特定任務的注意力頭的輸出進行平均
    • 透過在一個範例上微調模型
    • 透過讀取最終的softmax機率
  3. What did the function-vector paper observe after injecting a vector into a zero-shot prompt?
    • The model always crashed
    • It guaranteed correct answers on any task
    • It could trigger the associated task in the tested settings
    • It permanently changed the model weights
  4. 哪種分析技術支援找到帶有函數向量的頭部?
    • 損失的梯度下降
    • 集束搜尋
    • Dropout正規化
    • 因果中介分析
  5. What do function-vector experiments provide evidence for?
    • Some models form reusable internal representations associated with tasks
    • All language models only memorize text
    • Every model has one universal task vector
    • Tokenization alone determines every behavior
  6. Why are function vectors interesting to steering research?
    • They guarantee safe or correct behavior
    • They provide an activation-level intervention that can influence task behavior in tested settings
    • They eliminate prompts for every application
    • They make all model decisions fully transparent
  7. At what part of the transformer did the paper report strong function-vector effects?
    • Only the input embedding table
    • Only the final output logits
    • Middle layers in the tested models
    • 分詞器詞彙
  8. What happened when researchers summed some function vectors?
    • The vectors always canceled to zero
    • The model’s weights were permanently updated
    • Every possible task was composed perfectly
    • Some combinations triggered new complex tasks in the tested experiments