passdrill
AI & LLM Engineering · Evaluation, Testing & Safety · Card 001/010 easy

When evaluating an autoregressive language model on the same held-out test set, Model A gets a perplexity of 18.4 and Model B gets a perplexity of 42.1. Holding the tokenizer and test set fixed, what does this comparison indicate about the two models?

  1. Model B is better, because a higher perplexity score means the model assigns more probability mass to a wider range of plausible continuations, which reflects greater linguistic flexibility
  2. Neither score is meaningful on its own; perplexity only becomes interpretable once the model has also been evaluated on a downstream task such as translation or summarization
  3. Model A is better at predicting this test text than Model B, because perplexity is derived from the model's average per-token negative log-likelihood, and a lower value means the model assigned higher probability, on average, to the tokens that actually occurred
  4. Model A used a larger training corpus than Model B, since perplexity is primarily a measure of how much data a model was trained on rather than of its predictive accuracy
Next card → Shuffle