Ikibazo gihuza ibibazo · Biragoye Urwego

Imikorere Vector hamwe ninshingano zabajijwe Ikibazo

Wige uburyo imikorere yimikorere ikurwa mumitwe yitabwaho, igaterwa mubintu byihishe, kandi ikageragezwa murwego rwibikorwa.

Ikibazo 1 Bya 8

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

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  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. Nigute imikorere yimikorere isanzwe yubatswe?
    • Mugukusanya amagambo yose yashyizwemo mumagambo
    • Mugereranije ibisubizo byibikorwa byihariye bitwara imitwe hejuru yintangarugero
    • Mugutunganya neza icyitegererezo kurugero rumwe
    • Mugusoma amaherezo ya softmax bishoboka
  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. Ni ubuhe buryo bwo gusesengura bushimangira gushakisha imitwe itwara imikorere ya vector?
    • Kugabanuka gahoro gahoro kubihombo
    • Gushakisha ibiti
    • Kureka guta
    • Isesengura ry'abunzi
  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
    • Ikimenyetso cyamagambo
  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