Ikibazo gihuza ibibazo · Hagati Urwego

Kwangwa Gutoranya Ikibazo Cyiza

Hindura ibisekuruza byabakandida no kuyungurura, kugenzura ibihembo bishingiye, kugenzura imyitozo, hamwe ningaruka zo guhitamo amanota atagira inenge.

Inzira zijyanye no kuyoboraKwangwa Gutoranya neza
Ikibazo 1 Bya 8

Nuwuhe muzingo usobanura neza uburyo Kwangwa Gutoranya Cyiza-Guhuza bitezimbere icyitegererezo?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nuwuhe muzingo usobanura neza uburyo Kwangwa Gutoranya Cyiza-Guhuza bitezimbere icyitegererezo?
    • Tanga ibisubizo byinshi byabakandida, komeza utange amanota meza, kandi ubigumane
    • Siba ibyakozwe nabi cyane
    • Wange amakuru yose yo guhugura hanyuma utangire hejuru
    • Icyitegererezo rimwe kandi burigihe wemere ibisohoka
  2. Mubishobora kugenzurwa nkimibare cyangwa code, niki gishobora kuba ibihembo?
    • Icyitegererezo cyo kwiga ibihembo gusa
    • Niba igisubizo ari cyo cyangwa ibizamini biratsinda
    • Uburebure bw'igisubizo
    • Umubare wibimenyetso byatanzwe
  3. Which model family does the cited paper describe using rejection sampling in its alignment pipeline?
    • GPT-4o
    • BERT Base
    • Meta’s Llama 2-Chat
    • Whisper Large
  4. Why might a team choose rejection-sampling fine-tuning over a policy-gradient approach for some tasks?
    • It never needs a candidate generator or scoring rule
    • It guarantees no reward hacking
    • It always requires less compute than every RL method
    • It can use supervised learning on selected generations instead of updating through policy-gradient RL
  5. Amahugurwa kuri sample-bihembo byintangarugero akora iki?
    • Kugaragaza ibyiza-bya-N ubuziranenge bw'icyitegererezo kimwe-icyitegererezo gisohoka
    • Yongera ingano yamagambo
    • Kuraho ubushobozi bwicyitegererezo cyo kubyara inyandiko
    • Kabiri ibipimo bibarwa
  6. What should teams monitor when repeatedly fine-tuning on filtered model-generated outputs?
    • Gusa umubare wikitegererezo
    • Output diversity alongside held-out correctness
    • Whether every answer uses the same wording
    • Only the training loss on selected samples
  7. What is a limitation of rejection-sampling fine-tuning’s candidate selection?
    • It can only be used with image labels
    • It always changes the tokenizer
    • It cannot train on a high-quality answer that was never generated or retained
    • It makes the scoring function unnecessary
  8. What risk arises if the scoring model used to filter candidates is flawed?
    • The policy becomes unable to generate any text
    • The tokenizer automatically changes vocabulary
    • The reference labels become unnecessary
    • The policy may learn to exploit the scorer rather than improve the intended quality