quiz bu lëkkale ak tegtal · Dëgër Niveau

Modèlu embedding yu baax ngir quiz recuperation

Test ñaari positif ak negatif yu dëgër, ñàkka wuute ngir tàggat yaram, ak ni ñuy nattee ak moytu njuumte negatif ci RAG retrieval.

Laaj 1 de 8

Lan mooy negatif bu dëgër ci samp fine-tuning?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan mooy negatif bu dëgër ci samp fine-tuning?
    • A passage that looks relevant to the query but does not answer it
    • A passage from a different language
    • Any randomly chosen passage
    • A query with no answer
  2. Lan moo waral negatif yu dëgër yi gëna am njariñ negatif yu yomb yi?
    • They are cheaper to store
    • The base model already separates easy negatives, so hard ones teach new distinctions
    • They remove the need for positives
    • They shorten training time to zero
  3. Luy njuumte ci mbir mii?
    • A positive pair with a typo
    • A mined negative that actually does answer the query
    • A query that retrieves nothing
    • A vector with all zeros
  4. Ban perte lañuy faral di jëfandikoo ngir tàggat xeetu embedding ci ñaari laaj-paas?
    • Mean squared error on token counts
    • A contrastive loss such as InfoNCE (MultipleNegativesRankingLoss)
    • Cross-entropy on next-word prediction only
    • Hinge loss on image pixels
  5. Ginaaw boo soppi ci xeetu embedding bu bees, lan ngay def ci sa index dokimaa?
    • Nothing; old vectors still work
    • Re-embed the entire collection with the new model
    • Delete half the documents
    • Convert vectors to text
  6. Which alternative might give larger gains than fine-tuning with less effort?
    • Removing all metadata
    • Improving chunking, adding BM25 hybrid search or a reranker
    • Using a smaller context window
    • Lowering the embedding dimension to 2
  7. Which metrics does the guide recommend for evaluating retrieval?
    • BLEU and ROUGE
    • recall@k and nDCG@10
    • Perplexity only
    • Training loss only
  8. Why should synthetic questions generated from documents be filtered?
    • They are always in the wrong language
    • They often copy the document's wording, making the task too easy
    • They cannot be embedded
    • They violate the loss function