Maswali yanayounganishwa na mwongozo · Kati Kiwango

Perplexity na Maswali ya Vipimo vya Lugha

Kagua uwezekano wa tokeni ya marejeleo, mtambuka, misingi inayofanana, uwekaji tokeni unaolinganishwa, BLEU, viwango vya ubora, madirisha ya muktadha na miundo iliyofunikwa.

Njia za mwongozo zinazohusianaPerplexity Na Vipimo vya Lugha
Swali 1 ya 8

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

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  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. Muundo huweka uwezekano sawa katika msamiati wa maneno 10,000 bila kujifunza. Kuchanganyikiwa kwake ni nini?
    • 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
    • Wastani wa hitilafu ya pikseli za mraba
    • Hesabu ya parameta ya mfano
    • BLEU
  6. Ni kizuizi gani kikuu kinachosukuma watafiti zaidi ya kufadhaika kwa kuhukumu ubora wa ulimwengu halisi?
    • Perplexity hupima ubashiri wa neno linalofuata, si kama tokeo ni muhimu, kweli, au msaada
    • Perplexity ni ghali sana kukokotoa
    • Perplexity haiwezi kuhesabiwa kwenye data ya maandishi
    • Perplexity hufanya kazi tu wakati wa makisio, sio mafunzo
  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