Test legat de ghid · Mediu Nivel

Perplexity și Chestionar privind valorile lingvistice

Review reference-token likelihood, cross-entropy, uniform baselines, comparable tokenization, BLEU, quality limits, context windows, and masked models.

Căi de ghidare aferentePerplexity Și metrica limbii
Întrebare 1 de 8

Under the same autoregressive text-scoring setup, what does lower perplexity indicate?

Previzualizează fiecare întrebare8 întrebări

Răspunsurile și explicațiile apar pe măsură ce susțineți testul.

  1. Under the same autoregressive text-scoring setup, what does lower perplexity indicate?
    • Lower average negative log-likelihood for the reference tokens
    • A guarantee of more factually correct generated answers
    • A guarantee of a larger parameter count
    • A requirement that every top-choice prediction be correct
  2. Using natural-log negative log-likelihood, how is autoregressive perplexity computed from its average?
    • By multiplying the parameter count by the context length
    • By subtracting the average from the number of attention heads
    • By taking the average learning rate
    • By exponentiating the average negative log-likelihood
  3. Un model atribuie probabilitate uniformă într-un vocabular de 10.000 de cuvinte fără învățare. Care este nedumerirea sa?
    • 1
    • 10.000
    • 0
    • 100
  4. Why do tokenizer and corpus settings matter when directly comparing per-token perplexity values?
    • Perplexity ignores every scored reference token
    • All corpora necessarily produce the same likelihood
    • They change the units or reference data over which probabilities are averaged
    • Only model parameter count determines the score
  5. Which translation-reference metric uses modified n-gram precision and a brevity penalty?
    • Perplexity
    • Eroare medie de pixeli la pătrat
    • Numărul de parametri ai modelului
    • BLEU
  6. Ce limitare cheie îi împing pe cercetători dincolo de nedumerire pentru a judeca calitatea din lumea reală?
    • Perplexity măsoară predicția cuvântului următor, nu dacă rezultatul este util, adevărat sau util
    • Perplexity este prea scump pentru a fi calculat
    • Perplexity nu poate fi calculat pe date text
    • Perplexity funcționează numai în timpul inferenței, nu al antrenamentului
  7. When scoring a long text with a fixed-context model, what can a sliding-window procedure provide that disjoint chunks lose near boundaries?
    • A new vocabulary learned automatically at every boundary
    • A guarantee that generated answers are factually correct
    • More preceding context for the scored target tokens
    • A requirement to count each overlapping target repeatedly
  8. Why is conventional left-to-right perplexity not directly the same score for a BERT-style masked language model?
    • BERT has no learned parameters
    • The masked model does not directly define the same autoregressive sequence factorization
    • Every masked-token probability is necessarily zero
    • Perplexity is defined only for image pixels