Kediska Quseeya Marginal ee ugu badan

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay dhibaatada aasaasiga ah ee MMR loogu talagalay in lagu xalliyo?
   • Daahitaanka su'aalaha qunyar socodka ah ee kaydadka waaweyn
   • Higaada khaldan ee weydiimaha isticmaalaha
   • Natiijooyin badan oo nuqul ka mid ah ayaa ka yimid qiimeynta khuseysa saafiga ah
   • La'aanta xogta tababarka ee ku-xidhka
2. Qaabka MMR, waa maxay qiimaha lambda ee ku dhow 1 xoogga saaraya?
   • Xidhiidhka saafiga ah ee weydiinta
   • Kala duwanaanshaha ugu badan ee natiijooyinka
   • Miisaanka siman ee dhammaan musharraxiinta
   • Xulasho random
3. Sidee MMR u doorataa natiijooyinkeeda?
   • Dhammaan hal mar adoo kala saaraya hal dhibic
   • Si aan kala sooc lahayn oo leh abuur go'an
   • Sida alifbeetada u kala horreeyaan
   • Hungurinimo, midba mar, marka la barbar dhigo shayada hore loo doortay
4. How can an embedding-based MMR implementation measure query relevance and document redundancy?
   • Using only a document's filename length
   • Using a similarity measure such as cosine, without MMR requiring that one measure universally
   • Using a mandatory audio-transcription score for all text
   • Using no relevance or inter-document comparison at all
5. Maxay MMR si gaar ah faa'iido ugu leedahay jiilka la kordhiyay (RAG)?
   • Waxay bixisaa cadaymo dhammaystiran, oo aan la soo celin karin
   • Waxay cadaadisaa miisaanka moodeelka
   • Si toos ah ayey u habaynaysaa qaabka luqadda
   • Waxay siraysaa dukumentiyada la soo saaray
6. If MMR caches each candidate's maximum redundancy and updates it against each new selection, roughly how many similarities are needed for k picks from n candidates?
   • Always constant time independent of k and n
   • Exactly n factorial for every implementation
   • About k times n, ignoring vector dimension and initial setup
   • No document comparisons after the first query score
7. With lambda equal to 0.5, relevance 0.8, and maximum selected-item similarity 0.9, what is a candidate's MMR scoring term?
   • 0.85, from averaging the two similarities
   • Minus 0.05, from 0.5 times 0.8 minus 0.5 times 0.9
   • 0.72, from multiplying relevance and redundancy
   • 1.7, from adding the two similarities
8. Can an MMR reranker select a relevant document that the upstream retrieval candidate pool omitted?
   • Yes; diversity scoring invents missing source documents
   • Yes; a lower lambda automatically searches the whole corpus
   • Yes; reranking changes the document's original publication date
   • No; it chooses among the supplied candidates unless the upstream pool is expanded