Best-of-N Sampling ak Quiz bu bees

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy xalaat bu mag bi ci sampling bi gëna baax ci N?
   • Defar N njariñu kàndidaa yi nga tann ki gëna am poñ
   • Taggat model bi N yoon nga moyenne poid yi
   • Jëfandikool li model bi njëkka génne rek
   • Wàññil baat yi ba N token
2. When is best-of-N most likely to help?
   • When every output is equally good
   • When the model sometimes samples a correct candidate and a reliable verifier can identify it
   • When the task has no way to assess candidates
   • When sampling is disabled
3. Lan mooy wane ndax best-of-N mooy gëna baaxal resultaa yi?
   • Kulòoru interfaasu jëfandikukat bi
   • Guddaayig laaj bi kese
   • Kalite ak dëgëraay bu dugal poñ yi wala saytukat bi
   • Dayo vocabulaire model bi
4. What can happen when N becomes large and the reward model is an imperfect proxy?
   • The model’s tokenizer is removed
   • The model forgets its training weights
   • All candidates become identical
   • Selection can favor outputs that exploit scorer errors and reduce true quality
5. Ban pexem ranging bu yomb lañuy woowe dëppoo sa bopp?
   • Wote yu ëpp ci tontu yiñ tànn
   • Tann tontu bi gëna gudd
   • Tann misaal bu bari
   • Deel faral di jël li gëna néew wërsëg
6. What mainly drives the generation cost of best-of-N?
   • Only the number of vocabulary entries
   • The total amount of text generated across the sampled candidates
   • The user interface color
   • The number of model training runs
7. If each independent sample succeeds with probability p and a perfect verifier picks any success, what is the chance at least one of N samples succeeds?
   • p/N
   • N−p
   • 1−(1−p)^N
   • 1−p^N
8. Which assumption is needed for the simple 1−(1−p)^N success formula?
   • Every response has a different length
   • The model is retrained after each sample
   • The reward model has no parameters
   • The candidate samples are independent and the verifier recognizes success perfectly