Guide-yakabatana mibvunzo · Pakati Nhanho

Maitiro ekutarisa kweMath Reasoning Quiz

Ongorora maitiro uye mhinduro yemhedzisiro, ine PRM800K zvinyorwa, kusarudzwa kwevamiriri, kutariswa kweMath-Shepherd, uye nhanho-yepakati aggregation.

Nzira dzekutungamira dzinoenderanaProcess Supervision yeMath Reasoning
Mubvunzo 1 ye 8

Where does process supervision provide feedback compared with outcome supervision?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  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. Sei mhedzisiro-kutarisa chete kungave kutsausa kumatambudziko esvomhu?
    • Inononoka kuverenga
    • Haikwanise kubata decimal
    • Zvinoda magiredhi evanhu padambudziko rega rega
    • Modhi inogona kusvika pamhinduro chaiyo kuburikidza nematanho asina kunaka anoitika kudzima
  3. Chii chakaburitswa ne OpenAI pamwe ne 'Ngationese Nhanho Nenhanho'?
    • PRM800K, dataset ye ~ 800,000 nhanho-nhanho zvinyorwa
    • Iyo nyowani GPU yekuvakisa
    • Iyo GSM8K bvunzo seti
    • Injini ye 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. Ndeipi nzira inoderedza kudiwa kwematanho enhanho emunhu anodhura?
    • Kudzima modhi yemubairo zvachose
    • Monte Carlo kuburitswa kunofungidzira kukosha kwenhanho yega yega (semuenzaniso, Math-Shepherd)
    • Kushandisa mhinduro yekupedzisira chete
    • Kudzidziswa pamimwe mitauro
  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