Ikibazo gihuza ibibazo · Hagati Urwego

Kugenzura Inzira Kubibazo Byibibazo

Suzuma inzira n'ibisubizo byatanzwe, hamwe na label ya PRM800K, guhitamo abakandida, kugenzura imibare-Umwungeri, hamwe no guteranya intambwe.

Inzira zijyanye no kuyoboraKugenzura Inzira Kubitekerezo
Ikibazo 1 Bya 8

Where does process supervision provide feedback compared with outcome supervision?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Where does process supervision provide feedback compared with outcome supervision?
    • Only at the physical GPU temperature
    • At intermediate reasoning steps rather than only the final result
    • Only at the document filename
    • Only at an increased vocabulary size
  2. Ni ukubera iki kugenzura ibisubizo gusa bishobora kuyobya ibibazo by'imibare?
    • Biratinda cyane kubara
    • Ntishobora gukora decimals
    • Irasaba abiga amanota yabantu kuri buri kibazo
    • Icyitegererezo kirashobora kugera kubisubizo nyabyo binyuze mu ntambwe zitagira ingano zibaho kugirango uhagarike
  3. Niki OpenAI yasohoye hamwe nakazi ka 'Reka dusuzume intambwe ku yindi'?
    • PRM800K, dataset ya ~ 800.000 intambwe-urwego rwikirango
    • Ubwubatsi bushya bwa GPU
    • Ikizamini cya GSM8K
    • Moteri ya chess
  4. In best-of-N math selection with a process reward model, what does the verifier do?
    • Guarantees that a correct candidate was generated
    • Changes every tokenizer token into a proof axiom
    • Scores generated candidate solutions under the chosen aggregation rule
    • Replaces the original problem with a translation
  5. Nubuhe buryo bugabanya gukenera ibirango bihenze byabantu?
    • Guhagarika ibihembo byigihembo rwose
    • Monte Carlo izunguruka igereranya agaciro ka buri ntambwe mu buryo bwikora (urugero, Imibare-Umwungeri)
    • Gukoresha igisubizo cyanyuma
    • Amahugurwa ku ndimi nyinshi
  6. What can low step-level verifier scores usefully indicate to someone reviewing a solution?
    • Steps that merit closer inspection
    • An infallible location of the first actual error
    • A mathematical proof that all other steps are correct
    • The exact temperature used to sample every token
  7. For step scores 0.9 and 0.8, what is the solution score under a product aggregation rule?
    • 0.8
    • 0.85
    • 1.7
    • 0.72
  8. Which data-selection strategy did Let’s Verify Step by Step study to improve labeling efficiency?
    • Choosing examples only by alphabetical filename order
    • Removing every incorrect-answer candidate from the labeling pool
    • Active learning that selected informative candidate solutions
    • Using an unlabeled test answer as the final human label