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。
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。
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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