Kuiz berkaitan panduan · Sederhana Tahap
Perplexity dan Kuiz Metrik Bahasa
Semak kemungkinan token rujukan, entropi silang, garis dasar seragam, tokenisasi setanding, BLEU, had kualiti, tetingkap konteks dan model bertopeng.
soalan 1 daripada 8
Under the same autoregressive text-scoring setup, what does lower perplexity indicate?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- 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
- 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
- Model memberikan kebarangkalian seragam merentas perbendaharaan kata 10,000 perkataan tanpa pembelajaran. Apakah kebingungannya?
- 1
- 10,000
- 0
- 100
- 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
- Which translation-reference metric uses modified n-gram precision and a brevity penalty?
- Perplexity
- Min ralat piksel kuasa dua
- Kiraan parameter model
- BLEU
- Apakah batasan utama yang mendorong penyelidik melampaui kebingungan untuk menilai kualiti dunia sebenar?
- Perplexity mengukur ramalan perkataan seterusnya, bukan sama ada output berguna, benar atau membantu
- Perplexity terlalu mahal untuk dikira
- Perplexity tidak boleh dikira pada data teks
- Perplexity hanya berfungsi semasa inferens, bukan latihan
- 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
- 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