Penyeliaan Proses untuk Kuiz Penaakulan Matematik

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

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. Mengapakah penyeliaan hasil sahaja boleh mengelirukan untuk masalah matematik?
   • Ia terlalu lambat untuk mengira
   • Ia tidak boleh mengendalikan perpuluhan
   • Ia memerlukan penggred manusia untuk setiap masalah
   • Model boleh mencapai jawapan yang betul melalui langkah-langkah cacat yang berlaku untuk membatalkan
3. Apakah yang OpenAI keluarkan bersama 'Mari Sahkan Langkah demi Langkah' berfungsi?
   • PRM800K, set data sebanyak ~800,000 label peringkat langkah
   • Seni bina GPU baharu
   • Set ujian GSM8K
   • Enjin catur
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. Apakah pendekatan yang mengurangkan keperluan untuk label langkah manusia yang mahal?
   • Melumpuhkan model ganjaran sepenuhnya
   • Pelancaran Monte Carlo yang menganggarkan nilai setiap langkah secara automatik (cth., Math-Shepherd)
   • Hanya menggunakan jawapan akhir
   • Latihan mengenai lebih banyak bahasa
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