Habraaca Kormeerka Kediska Sababta Xisaabta

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

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. Maxay tahay sababta kormeerka natiijada-kaliya ay ugu marin habaabiso dhibaatooyinka xisaabta?
   • Aad bay u gaabis tahay in la xisaabiyo
   • Ma xamili karo jajab tobanle
   • Waxay u baahan tahay darajooyin aadanaha dhibaato kasta
   • Qaabku wuxuu ku gaari karaa jawaabta saxda ah tillaabooyin khaldan oo dhaca si meesha looga saaro
3. Maxay OpenAI sii daysay oo ay weheliso shaqada 'Aan ku Xaqiijinno Talaabo Tallaabo'?
   • PRM800K, kayd xog ~ 800,000 heer-tallaabo ah
   • Dhismaha GPU cusub
   • Tijaabada GSM8K
   • Matoorka 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. Qaabkee ayaa hoos u dhigaya baahida loo qabo sumadaha tillaabada qaaliga ah ee aadanaha?
   • Deminta qaabka abaalmarinta gabi ahaanba
   • Monte Carlo waxay soo bandhigtay qiimeeyay tilaabo kasta qiimaheeda si toos ah (tusaale, Xisaab-Shepherd)
   • Isticmaalka kaliya jawaabta ugu dambeysa
   • Tababar ku saabsan luqado badan
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