quiz bu lëkkale ak tegtal · Diggante Niveau

Ranking model Quiz

Saytu cër yi retriever yi ak reranker yi, méngale encodeur yu wuute yi ak bi-encodeur yi, nga xoolaat limu ensemble kàndidaa yi.

Yooni njiit yu jëm ciRaññewaat ay model
Laaj 1 de 8

Ci pipeline recuperation bu am ñaari etap, lan mooy liggéeyu reranker bi?

Xoolaatal laaj bu nekk8 laaj

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

  1. Ci pipeline recuperation bu am ñaari etap, lan mooy liggéeyu reranker bi?
    • Ngir joxaat poñ yi ak defaraat limu kàndidaa yi ngir am njariñ
    • Ngir dindi kàndidaa yu njëkk yi ci ay milioŋ ciy këyit
    • Ngir denc këyit ci benn base de done
    • Ngir defar tontu bu mujj ci làkk wiñ nàmp
  2. Besides MS MARCO, on which dataset did Nogueira and Cho report strong results for their BERT passage reranker?
    • Nataal Net
    • TREC-CAR
    • Kaddu Libri
    • SQuAD only
  3. Lu tax mënu ñu jëfandikoo cross-encoder ngir seetee ay milioŋ ciy këyit ci saasi?
    • Ci nataal kese lay dox
    • Mënul jàng mbind
    • Dañu wara xayma poñ yi ci dokimaa-laaj bu nekk, te loolu dafa yeex ci escalier bi
    • Du soxla benn xayma
  4. Lan mooy njariñu bi-encoder ci cross-encoder?
    • Dafa gëna dëggu ci relevansi bu ndaw
    • Saa yu nekk dafay raññewaat resultaa yi ci anam wu jaar yoon
    • Soxlawul ay done tàggat
    • Dokimaa yiñ ci samp mën nañu leen njëkka xayma, suko defee ñu gaaw ci seet te mën nañu ko yokk
  5. How can a reranker affect context quality in a retrieval-augmented generation pipeline?
    • It can move more relevant retrieved candidates higher in the context shortlist, but does not guarantee correctness
    • It ensures every retrieved passage is factually correct
    • It creates missing documents in the corpus
    • It removes the need to evaluate retrieval
  6. In listwise reranking, what does the model consider together?
    • Only one document with no query
    • A query and a set of candidate documents when deciding their ordering
    • Each document embedding before any candidate retrieval
    • A single relevance label for the full training corpus
  7. What should a team verify before interpreting reranker scores as probabilities?
    • Whether every score is above zero
    • Whether the first-stage retriever was removed
    • Whether the scores have been calibrated and evaluated for that use
    • Whether the model has more parameters than the retriever
  8. What limitation does a reranker inherit from the first-stage retrieval system?
    • It always returns a calibrated probability
    • It removes the need for retrieval
    • It guarantees a correct generated answer
    • It cannot promote a relevant document that was never included in the candidate set